Canadian Journal of Chemical Engineering最新文献_第2页

Artificial intelligence and machine learning at various stages and scales of process systems engineering

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-11-06 DOI: 10.1002/cjce.25525

Karthik Srinivasan, Anjana Puliyanda, Devavrat Thosar, Abhijit Bhakte, Kuldeep Singh, Prince Addo, Rajagopalan Srinivasan, Vinay Prasad

{"title":"Artificial intelligence and machine learning at various stages and scales of process systems engineering","authors":"Karthik Srinivasan, Anjana Puliyanda, Devavrat Thosar, Abhijit Bhakte, Kuldeep Singh, Prince Addo, Rajagopalan Srinivasan, Vinay Prasad","doi":"10.1002/cjce.25525","DOIUrl":"https://doi.org/10.1002/cjce.25525","url":null,"abstract":"We review the utility and application of artificial intelligence (AI) and machine learning (ML) at various process scales in this work, from molecules and reactions to materials to processes, plants, and supply chains; furthermore, we highlight whether the application is at the design or operational stage of the process. In particular, we focus on the distinct representational frameworks employed at the various scales and the physics (equivariance, additivity, injectivity, connectivity, hierarchy, and heterogeneity) they capture. We also review AI techniques and frameworks important in process systems, including hybrid AI modelling, human-AI collaborations, and generative AI techniques. In hybrid AI models, we emphasize the importance of hyperparameter tuning, especially in the case of physics-informed regularization. We highlight the importance of studying human-AI interactions, especially in the context of automation, and distinguish the features of human-complements-AI systems from those of AI-complements-human systems. Of particular importance in the AI-complements-human framework are model explanations, including rule-based explanation, explanation-by-example, explanation-by-simplification, visualization, and feature relevance. Generative AI methods are becoming increasingly relevant in process systems engineering, especially in contexts that do not belong to ‘big data’, primarily due to the lack of high quality labelled data. We highlight the use of generative AI methods including generative adversarial networks, graph neural networks, and large language models/transformers along with non-traditional process data (images, audio, and text).","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 3","pages":"1004-1035"},"PeriodicalIF":1.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cjce.25525","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143112677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Issue Highlights 发行亮点

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-11-06 DOI: 10.1002/cjce.25003

引用次数: 0

Modelling and optimization of amoxicillin degradation over ZnO and glucose oxidase modified TiO2 nanowire 氧化锌和葡萄糖氧化酶修饰的二氧化钛纳米线降解阿莫西林的建模与优化

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-10-20 DOI: 10.1002/cjce.25493

Somayeh Sohrabi, Mostafa Keshavarz Moraveji

{"title":"Modelling and optimization of amoxicillin degradation over ZnO and glucose oxidase modified TiO2 nanowire","authors":"Somayeh Sohrabi, Mostafa Keshavarz Moraveji","doi":"10.1002/cjce.25493","DOIUrl":"https://doi.org/10.1002/cjce.25493","url":null,"abstract":"Recently, antibiotics posing threats to health and the environment have been highlighted. According to previous reports, amoxicillin is the most hazardous antibiotic in Tehran. In order to overcome the risks associated with the storage and contamination of oxidizing agents, a Janus structure of Ti/TiO2/FA/GOx/ZnO is introduced for in situ steady generation and consumption of H2O2. The most efficient nanowire structure of TiO2 is achieved at 140°C and 4.5 h. The footprints of GOx as the bioactive site to produce H2O2 and ZnO as the photoactive site to dope TiO2 have been proved by Raman, Fourier transform infrared (FTIR), X-ray diffraction (XRD), differential scanning calorimetry (DSC), scanning electron microscopy (SEM), and transmission electron microscopy (TEM) analyses. For the first time, a Minimum Run Resolution V screening has been implemented for seven factors in an amoxicillin degradation process by the so-called bio-photo-catalyst. According to analysis of variance (ANOVA), the significance of the three most important variables is as follows: amoxicillin concentration (C) > the area covered by TiO2 nanowires (E) > ZnO/GOx (F) ratio. The significance of the model over the 95% confidence interval is confirmed by R2 of 0.9970, F-value of 108.10.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 4","pages":"1683-1700"},"PeriodicalIF":1.6,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143582095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Issue Highlights 发行亮点

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-10-06 DOI: 10.1002/cjce.25001

引用次数: 0

Assuring optimality in surrogate-based optimization: A novel theorem and its practical implementation in pressure swing adsorption optimization

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-09-24 DOI: 10.1002/cjce.25512

Carine Menezes Rebello, Erbet Almeida Costa, Antonio Santos Sánchez, Fredy Vides, Idelfonso B. R. Nogueira

{"title":"Assuring optimality in surrogate-based optimization: A novel theorem and its practical implementation in pressure swing adsorption optimization","authors":"Carine Menezes Rebello, Erbet Almeida Costa, Antonio Santos Sánchez, Fredy Vides, Idelfonso B. R. Nogueira","doi":"10.1002/cjce.25512","DOIUrl":"https://doi.org/10.1002/cjce.25512","url":null,"abstract":"Surrogate-based optimization has gained significant traction in several engineering fields, given its ability to handle complex systems without significant computational burdens. However, surrogate models are approximations and may have limitations, including the possibility of artificial minima. The main contribution of this work is the derivation of a robustness test that guarantees the optimality of surrogate-based optimization. The derivation of this metric is based on the universal approximation theorem. The full framework proposed in this work is also composed by a sampling sizing methodology to randomly select samples within a feasible operating region (FOR) resulting from the optimization population, reducing the computational cost of the analysis and avoiding biases in the robustness calculation. The applicability and importance of this methodology are demonstrated through a case study of a complex chemical process—a pressure swing adsorption (PSA) unit—which presents a high computational cost to solve optimization problems. The results highlight the need and importance of evaluating the optimality of surrogate-based optimization schemes.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 3","pages":"1036-1059"},"PeriodicalIF":1.6,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cjce.25512","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143118994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identifying design criteria for implementing inherent safety in chemical process industries part 2: Design mechanism 确定实施化学过程工业固有安全的设计标准。第2部分：设计机制

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-09-23 DOI: 10.1002/cjce.25497

Zafirah Zakaria, Kamarizan Kidam, Mimi H. Hassim

{"title":"Identifying design criteria for implementing inherent safety in chemical process industries part 2: Design mechanism","authors":"Zafirah Zakaria, Kamarizan Kidam, Mimi H. Hassim","doi":"10.1002/cjce.25497","DOIUrl":"https://doi.org/10.1002/cjce.25497","url":null,"abstract":"Inherent safety concepts are common knowledge today, but accidents with similar characteristics do recur. Research on accident causes found that design errors, especially equipment failure, contribute the highest percentage of accidents. The development of inherent safety tools has been increasing at a positive pace, but only a small number of these tools are applicable to equipment design. Ample amounts of inherent safety tools are only suitable to be used at the early design stage. This amplifies the fact that inherent safety tools are still conceptual (e.g., change process routes, change safer materials). This is in contrast to the circumstances, where tools are expected to reinforce the inherent safety of equipment. The objective of this research is to identify design mechanism that can help trigger design thinking for implementation of inherent safety in the chemical process industry. To identify such a design mechanism, 526 cases were collected, and knowledge of the mechanism was extracted from design changes and presented in this research paper. The mechanisms were classified according to equipment and inherent safety keywords. The significant design mechanisms from the overall summation were listed (turbulence, change heat transfer fluid, continuous removal, large surface area, corrosion resistance, seamless joint, thin film, dividing wall, on demand, and double wall).","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 1","pages":"63-81"},"PeriodicalIF":1.6,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Special issue section on process system safety and risk engineering 关于工艺系统安全和风险工程的特刊部分

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-09-18 DOI: 10.1002/cjce.25499

Abdallah S. Berrouk, K. Nandakumar

引用次数: 0

Complex network analysis for accident causes modelling to enhance process safety in chemical enterprises

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-09-16 DOI: 10.1002/cjce.25443

Songming Li, Guohua Chen, Lixing Zhou, Yimeng Zhao, Qiming Xu, Jie Zhao

{"title":"Complex network analysis for accident causes modelling to enhance process safety in chemical enterprises","authors":"Songming Li, Guohua Chen, Lixing Zhou, Yimeng Zhao, Qiming Xu, Jie Zhao","doi":"10.1002/cjce.25443","DOIUrl":"https://doi.org/10.1002/cjce.25443","url":null,"abstract":"Hazardous chemicals often cause catastrophic accidents, and accidents often result from intricate interactions among various causes. Due to the varying risk factors in different areas of chemical enterprises, to achieve more precise prevention, a more detailed study of the accident risk factors in each area is necessary. Therefore, this study focuses on analyzing critical accident causes and their interrelationships in different functional areas of chemical enterprises to enhance process safety by using a complex network model. Based on 90 accident information, complex network models are constructed for hazardous chemical warehouse areas (HCWAs), tank farm areas (TFAs), and production areas (PAs). Subsequently, a topological analysis of the complex network models is conducted. Based on the PageRank algorithm, 13 critical nodes are identified for HCWAs, while 14 for TFAs and 13 for PAs. Node degree analysis with confidence quantifies mutual influences, forming critical accident causal links for each area. The research results offer decision support for precise accident risk control, aiding in reducing future accidents and improving process system safety in chemical enterprises.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 2","pages":"679-696"},"PeriodicalIF":1.6,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143116095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of pre-aging intermediate layers on the performance of multi-layer organic photovoltaic devices 预老化中间层对多层有机光伏器件性能的影响

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-09-09 DOI: 10.1002/cjce.25487

Emma Su, Adam R. Tetreault, Lili Zheng, Marzieh Riahinezhad, Itzel Lopez-Carreon, Elnaz Esmizadeh, Peter Collins, Timothy P. Bender

{"title":"Effect of pre-aging intermediate layers on the performance of multi-layer organic photovoltaic devices","authors":"Emma Su, Adam R. Tetreault, Lili Zheng, Marzieh Riahinezhad, Itzel Lopez-Carreon, Elnaz Esmizadeh, Peter Collins, Timothy P. Bender","doi":"10.1002/cjce.25487","DOIUrl":"10.1002/cjce.25487","url":null,"abstract":"Understanding the degradation behaviour of organic photovoltaic (OPV) devices is an essential part to improve their stability prior to massive production. Accelerated aging can help to assess their stability and study the underlying degradation mechanisms of OPVs. Most studies focus on individual layers or a full device, and little is known about the role a pre-aged layer stack plays in the performance of a device. Herein, we report the investigation of the effects of pre-aging of multiple layers on the performance of OPVs. Instead of aging a single layer or an entire stack (sequential layers: ITO/PEDOT:PSS/MoOx/F-BsubPc/C60/BCP/Ag), our process involved aging the intermediate layer stack for 24 h after depositing a specific layer before continuing with the subsequent depositions to fully fabricate/manufacture OPVs. Aging was conducted under four controlled conditions considering parameters including moisture, gas type, and temperature in the absence of light according to the International Summit on Organic Photovoltaic Stability (ISOS) protocols. Short of PEDOT:PSS we found that multiple layers, being subjected to the parameters, resulted in a decline in OPV device performance after being fully manufactured. Device performance is evaluated based on short-circuit current density (Jsc), power conversion efficiency (PCE), and open-circuit voltage (Voc). Our analysis provides insight into the degradation mechanisms of layered/planar OPV structures and offers strategic guidance for optimizing fabrication processes, particularly during the layer deposition transitions. We recommend that during OPV vacuum deposited fabrication, intermediate layers should be protected from moisture, O2, high temperature, and even inert gases, preferably in a low-vacuum environment.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"102 12","pages":"4106-4119"},"PeriodicalIF":1.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Empirical prediction on boilover onset and impact for liquid hydrocarbon fire in atmospheric storage tank 常压储罐中液态碳氢化合物起火沸腾和影响的经验预测

IF 1.6 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2024-09-09 DOI: 10.1002/cjce.25485

Azizul Buang, Muhammad Ameer Zaaba, Muhammad Izham Mohd Yusof, Daneskumar Manogaran, Hani Tiara Faihana Hifni, Muhammad Roil Bilad

{"title":"Empirical prediction on boilover onset and impact for liquid hydrocarbon fire in atmospheric storage tank","authors":"Azizul Buang, Muhammad Ameer Zaaba, Muhammad Izham Mohd Yusof, Daneskumar Manogaran, Hani Tiara Faihana Hifni, Muhammad Roil Bilad","doi":"10.1002/cjce.25485","DOIUrl":"10.1002/cjce.25485","url":null,"abstract":"Boilover can occur several hours after the fuel in a storage tank caught fire. The delayed occurrence is an unknown strong parameter when managing the emergency response operations. Those managing response operations must be aware of the boilover potential and take the precautions to ensure safety. Modelling the phenomenon enables predicting crucial event features and assists in highlighting safety measures, with a key focus on the ignition-to-boilover time interval. This study focused on the predictive empirical tool development aimed at estimating the boilover onset time and consequences. This was achieved through series of small-scale boilover experiments, followed by validation using cases of boilover incidents. The results revealed a linear relationship between the boilover onset time and the initial depth of fuel. Consequently, an empirical correlation was derived to predict the time to boilover. The developed correlation has demonstrated its ability to offer conservative predictions while also exhibiting agreement with both the observed onset time and consequences of boilover events. The reported time to boilover for the Czechowice-Dziedzice incident is 1050 min, while the predicted time is 1413.2 min. The model showed reasonable agreement with the Amoco Refinery incident. The predicted boilover time of 811.3 min aligns with the boilover incident, reported as 790 and 925 min, respectively. It is evident that the empirical model can predict the time to boilover to a similar order of magnitude. Certain considerations in the development of effective strategies in handling fire scenario with boilover potentials can be assessed using the predictive tool developed.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 4","pages":"1701-1710"},"PeriodicalIF":1.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0