Canadian Journal of Chemical Engineering最新文献

筛选
英文 中文
A critical study of sustainable biocomposites developed from rheologically distinct poly(butylene adipate-co-terephthalate) (PBAT) reinforced with biocarbon from coconut (Cocos nucifera) for rigid applications 一项可持续生物复合材料的关键研究,由流变学独特的聚己二酸丁二酯-对苯二甲酸酯(PBAT)和椰子(Cocos nucifera)生物碳增强,用于刚性应用
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-04-03 DOI: 10.1002/cjce.25655
Blessing E. Itabana, Arturo Rodriguez-Uribe, Amar K. Mohanty, Manjusri Misra
{"title":"A critical study of sustainable biocomposites developed from rheologically distinct poly(butylene adipate-co-terephthalate) (PBAT) reinforced with biocarbon from coconut (Cocos nucifera) for rigid applications","authors":"Blessing E. Itabana,&nbsp;Arturo Rodriguez-Uribe,&nbsp;Amar K. Mohanty,&nbsp;Manjusri Misra","doi":"10.1002/cjce.25655","DOIUrl":"https://doi.org/10.1002/cjce.25655","url":null,"abstract":"<p>This study investigates the impact of rheological behaviour on the development of highly filled biocomposites for rigid applications using two grades of poly(butylene adipate-co-terephthalate) (PBAT). PBAT, a fully biodegradable polymer, has garnered significant attention as an alternative to non-biodegradable plastics in flexible packaging applications. However, increasing filler content in PBAT can enhance its stiffness, thereby expanding its potential for rigid applications. Filler incorporation is critically influenced by the polymer's flow behaviour, and excessive filler loading in a highly viscous matrix can lead to a decline in material's ease of processing and performance. This research is focused on the processing-performance evaluation of low melt flow (MFI) and high MFI PBAT filled biocarbon composites. While PBAT<sup>1</sup> supports up to 30 wt.% biocarbon, PBAT<sup>2</sup> can incorporate 50 wt.% biocarbon. Overall, at maximum filler loading, the mechanical and thermal performance of PBAT<sup>2</sup>-based composites were superior as compared to those of PBAT<sup>1</sup> composites. The tensile and flexural moduli of PBAT<sup>2</sup> composites increased by 122% and 171%, respectively. Additionally, the thermal stability showed a 38% improvement as compared to PBAT<sup>1</sup> composites. This study underscores the effect of the rheological properties on composites development and provides valuable insights for selecting optimal polymer matrices for high-filler, rigid applications.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 9","pages":"4301-4313"},"PeriodicalIF":1.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cjce.25655","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144767834","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
Hydrogen production and status in Canada: Foundations for a low-carbon future 加拿大的氢气生产和现状:低碳未来的基础
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-04-02 DOI: 10.1002/cjce.25620
Bahram Ghorbani, Sohrab Zendehboudi, Noori M. Cata Saady, Greg F. Naterer
{"title":"Hydrogen production and status in Canada: Foundations for a low-carbon future","authors":"Bahram Ghorbani,&nbsp;Sohrab Zendehboudi,&nbsp;Noori M. Cata Saady,&nbsp;Greg F. Naterer","doi":"10.1002/cjce.25620","DOIUrl":"https://doi.org/10.1002/cjce.25620","url":null,"abstract":"<p>Hydrogen (H<sub>2</sub>) has emerged as a promising solution for decarbonizing energy systems and driving economic growth. Canada's federal and provincial climate commitments, financial support, and expertise in clean technology and H<sub>2</sub> research and development are establishing the country as a leader in achieving net-zero carbon goals. This review paper provides a comprehensive study of the status, prospects, challenges, and opportunities associated with H<sub>2</sub> energy and the economy in Canada. The current state of H<sub>2</sub> energy infrastructure, including production facilities, distribution networks, and end-user applications across Canada is examined. Various H<sub>2</sub> production pathways utilizing different energy sources and feedstocks are analyzed. Key focus areas include steam methane reforming, water electrolysis, autothermal reforming, biomass gasification, and the integration of leading-edge technologies such as thermochemical cycles. The efficiency, costs, and environmental impacts of various H<sub>2</sub> production methods are assessed. Canada's H<sub>2</sub> production potential is examined across provinces, considering fossil fuel, nuclear, industrial thermal sources, and renewable energy sources such as wind, solar, biomass, and geothermal. Provincial strategies focus on regional strengths, with Alberta advancing blue H<sub>2</sub> production through carbon capture units and Quebec and British Columbia emphasizing green H<sub>2</sub> from hydroelectric and wind energy. The significant H<sub>2</sub> production projects and their applications across Atlantic, Central, and Western Canada are outlined. The main obstacles to establishing an H<sub>2</sub> economy in Canada are investigated, including economic challenges, policy gaps, technological limitations, infrastructure constraints, public awareness, subsidies, standardization, and safety concerns. Practical recommendations are offered to address these barriers, enabling the full potential of H<sub>2</sub> and supporting Canada's net-zero emission goals.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 9","pages":"4125-4171"},"PeriodicalIF":1.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144767675","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
Enhanced extraction of flaxseed oil, tocopherols, and fatty acids using supercritical carbon dioxide with ethanol: Process optimization and modelling 用超临界二氧化碳和乙醇强化提取亚麻籽油、生育酚和脂肪酸:过程优化和建模
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-04-01 DOI: 10.1002/cjce.25685
Aimin He, Nicky Rahmana Putra, Lailatul Qomariyah
{"title":"Enhanced extraction of flaxseed oil, tocopherols, and fatty acids using supercritical carbon dioxide with ethanol: Process optimization and modelling","authors":"Aimin He,&nbsp;Nicky Rahmana Putra,&nbsp;Lailatul Qomariyah","doi":"10.1002/cjce.25685","DOIUrl":"https://doi.org/10.1002/cjce.25685","url":null,"abstract":"<p>This study explores the extraction of flaxseed oil using supercritical CO<sub>2</sub> (SC-CO<sub>2</sub>) with ethanol as a co-solvent, optimizing key process parameters to enhance oil yield and total tocopherol content (TTC). The influence of pressure (20–30 MPa), temperature (40–60°C), and CO<sub>2</sub> flow rate (2–6 mL/min) was analyzed using response surface methodology (RSM). The optimal conditions (20 MPa, 51°C, 2 mL/min) yielded 36.86% oil and 112.71 ppm tocopherols, demonstrating the effectiveness of SC-CO<sub>2</sub> extraction. The addition of ethanol improved tocopherol and monounsaturated fatty acid (MUFA) recovery, while extraction without ethanol favoured polyunsaturated fatty acid (PUFA) retention. Gas chromatographic analysis confirmed that SC-CO<sub>2</sub> extraction produced a superior fatty acid profile compared to Soxhlet extraction, preserving higher levels of α-linolenic acid (ALA) and oleic acid. Solubility studies indicated that moderate pressure and temperature conditions enhance oil recovery. SC-CO<sub>2</sub> with ethanol proved to be an efficient and environmentally friendly alternative to conventional extraction methods, producing high-quality flaxseed oil rich in bioactive compounds. These findings support the scalability of SC-CO<sub>2</sub> extraction for nutraceutical, pharmaceutical, and food applications. Future research should explore antioxidant stability and large-scale processing feasibility to enhance industrial adoption.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"5094-5111"},"PeriodicalIF":1.9,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145037789","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
Density, viscosity, and stability of products from combinations of visbreaking and deasphalting 降粘和脱沥青组合产品的密度、粘度和稳定性
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-28 DOI: 10.1002/cjce.25694
Jose Beleno, Florian F. Schoeggl, Darius Remesat, Harvey W. Yarranton
{"title":"Density, viscosity, and stability of products from combinations of visbreaking and deasphalting","authors":"Jose Beleno,&nbsp;Florian F. Schoeggl,&nbsp;Darius Remesat,&nbsp;Harvey W. Yarranton","doi":"10.1002/cjce.25694","DOIUrl":"https://doi.org/10.1002/cjce.25694","url":null,"abstract":"<p>Transporting bitumen through pipelines in Western Canada is cost intensive because the oil has to be diluted with light solvents to meet pipeline specifications. The diluent requirement can be reduced by visbreaking (VIS) and solvent deasphalting (SDA), each of which decrease the viscosity and density of the oil. Combinations of the two processes can provide a greater viscosity and density reduction while minimizing the risk of asphaltene precipitation and coke formation. However, data on the product properties are required to assess these combined processes. In this study, a Western Canadian bitumen was visbroken at conversions from 24% to 42% and each product was then deasphalted with extents ranging from 50% to 96 wt.% asphaltene removal (VIS-SDA sequence). The same bitumen was deasphalted with extents from 30% to 96% and each deasphalted oil was then visbroken at conversions from 6% to 44% (SDA-VIS sequence). The following measurements were performed on the products: simulated distillation, gas yield, pentane-insoluble asphaltene content, toluene insoluble (TI) content, density, viscosity, and stability. Stability was assessed in terms of the onset of asphaltene precipitation from mixtures of oil and <i>n</i>-heptane. Neither the VIS-SDA nor the SDA-VIS sequence met the pipeline density specification, but both were able to reduce the diluent requirement to approximately 10 wt.% compared with 28 wt.% for the feed bitumen. The VIS-SDA sequence offered better product stability; however, the suitability of the separated asphaltenes for downstream processes has not been established. The SDA-VIS sequence produced usable asphaltenes but less stable oil products.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"4694-4707"},"PeriodicalIF":1.9,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cjce.25694","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038545","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
Study on the accessible pore volume coefficient of chemical flooding systems under different permeability, layer combination, and planar phase transition conditions 不同渗透率、层状组合、平面相变条件下化学驱体系可达孔隙体积系数研究
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-27 DOI: 10.1002/cjce.25668
Yanyong Wang, Jianguang Wei, Peng Ye, Lianbin Zhong, Dong Zhang, Guang Wang, Runnan Zhou, Anqi Shen, Xidong Ren
{"title":"Study on the accessible pore volume coefficient of chemical flooding systems under different permeability, layer combination, and planar phase transition conditions","authors":"Yanyong Wang,&nbsp;Jianguang Wei,&nbsp;Peng Ye,&nbsp;Lianbin Zhong,&nbsp;Dong Zhang,&nbsp;Guang Wang,&nbsp;Runnan Zhou,&nbsp;Anqi Shen,&nbsp;Xidong Ren","doi":"10.1002/cjce.25668","DOIUrl":"https://doi.org/10.1002/cjce.25668","url":null,"abstract":"<p>In this paper, first, the micro accessible efficiency of chemical flooding under different permeability reservoir conditions is studied by using nuclear magnetic resonance technology. Second, the macroscopic accessible efficiency of chemical agents under different types of sand body layer combinations was elucidated. Third, the macroscopic accessible pore volume correction coefficient of chemical agents under the phase transition conditions between injection and production wells was analyzed. Results show the following: (a) Permeability cannot be the only indicator for evaluating whether a reservoir is suitable for chemical flooding. (b) When the permeability grade ratio is less than 2.27 (10<sup>−3</sup> μm<sup>2</sup>/10<sup>−3</sup> μm<sup>2</sup>), the correction factor for macroscopic accessible pore volume of chemical agents is 1.00; when the permeability grade ratio has increased to 3.33, the macroscopic accessible pore volume correction factor for chemical agents in non-main sheet sand reservoirs is 0.68; and when the permeability grade ratio has increased to 16.67, the correction factor for macroscopic accessible pore volume of off balance sheet reservoir chemicals is 0.04. (c) The type and location of phase transition in sand bodies between injection and production wells have a significant impact on the macroscopic accessible volume coefficient of chemical agents. This part of the research is of great significance for selecting acid types based on reservoir properties.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 9","pages":"4608-4624"},"PeriodicalIF":1.9,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144768067","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
Investigation of selective denitrogenation of liquid fuel with different MIL-101 adsorbents 不同MIL-101吸附剂对液体燃料选择性脱氮的研究
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-26 DOI: 10.1002/cjce.25675
Mohamad Songolzadeh, Mansooreh Soleimani, Maryam Takht Ravanchi
{"title":"Investigation of selective denitrogenation of liquid fuel with different MIL-101 adsorbents","authors":"Mohamad Songolzadeh,&nbsp;Mansooreh Soleimani,&nbsp;Maryam Takht Ravanchi","doi":"10.1002/cjce.25675","DOIUrl":"https://doi.org/10.1002/cjce.25675","url":null,"abstract":"<p>In this work, three new structures of MIL-101 with a base metal of chromium (Cr), vanadium (V), and manganese (Mn) have been synthesized to improve selective adsorbing quinoline (QUI) from a liquid fuel. Different characterization tests were used to identify the specifications of the synthesized adsorbents; namely Brunauer–Emmett–Teller (BET), Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), and temperature-programmed desorption (TPD). Studies indicated that pseudo-first order and Langmuir isotherm are accurate and suitable models for determining kinetic and equilibrium data of QUI adsorption on these adsorbents. Based on the results, MIL-101 (Mn) had the highest maximum adsorption capacity of 70.08 (mg N · g<sup>−1</sup> ads.) in comparison to MIL-101 (Cr) and MIL-101 (V). For different adsorbents, the QUI/dibenzothiophene (DBT) selectivity was investigated by measuring of the adsorption of these components from their mixture. Finally, the QUI/DBT selectivity was in the following order of MIL-101 (Mn) &gt; MIL-101 (V) &gt; MIL-101 (Cr). Density functional theory (DFT) simulation was used to validate experimental results. Calculated bonding energies ratio for QUI and DBT indicated that MIL-101 (Mn) is the most selective adsorbent.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"4803-4813"},"PeriodicalIF":1.9,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038373","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
Impact of slug length in gas–liquid two-phase flow on the structural stress characteristics of horizontal rigid pipelines 气液两相流段塞长度对水平刚性管道结构应力特性的影响
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-26 DOI: 10.1002/cjce.25678
Abdalellah O. Mohmmed, Hussain H. Al-Kayiem, Abderraouf Arabi
{"title":"Impact of slug length in gas–liquid two-phase flow on the structural stress characteristics of horizontal rigid pipelines","authors":"Abdalellah O. Mohmmed,&nbsp;Hussain H. Al-Kayiem,&nbsp;Abderraouf Arabi","doi":"10.1002/cjce.25678","DOIUrl":"https://doi.org/10.1002/cjce.25678","url":null,"abstract":"<p>The intermittent passage of liquid slugs and gas pockets in slug flow generates substantial cyclic stress damage to piping systems and their supports. This issue poses significant challenges to the various industries in which this flow pattern is present. Despite their critical implications, the structural response to slug-induced forces has not yet been thoroughly elucidated. This study addresses this gap through a comprehensive experimental investigation of the influence of slug length on the structural integrity of pipes. A non-invasive image-processing technique was employed to measure the slug length, while biaxial strain gauges captured the pipe wall strain, accounting for Poisson and friction fluid–structure interaction (FSI) coupling mechanisms. The findings revealed a reduction in the induced stresses with increasing superficial liquid velocity and slug length. Furthermore, a semi-empirical model was developed by integrating slug length with the superficial gas and liquid velocities based on the slug unit concept to predict the structural stresses. The model provides a robust predictive framework for elucidating the relationship between slug length and induced stresses. However, its accuracy is influenced by the slug formation mechanism and various slug flow sub-regimes. The model demonstrated exceptional predictive capability, achieving a mean error of 6.2% and coefficient of determination of 93%.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"5124-5142"},"PeriodicalIF":1.9,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cjce.25678","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038374","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
A deep-learning model based on MFE-Transformer for chemical process fault detection 基于MFE-Transformer的化工过程故障检测深度学习模型
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-25 DOI: 10.1002/cjce.25689
Ying Xie, Xiaotong Wu, Yingjie Zhu, Yuan Zhu
{"title":"A deep-learning model based on MFE-Transformer for chemical process fault detection","authors":"Ying Xie,&nbsp;Xiaotong Wu,&nbsp;Yingjie Zhu,&nbsp;Yuan Zhu","doi":"10.1002/cjce.25689","DOIUrl":"https://doi.org/10.1002/cjce.25689","url":null,"abstract":"<p>Chemical process data usually exhibits strongly nonlinear characteristics, local information loss, and sample imbalance problems. These problems make it difficult for traditional models to accurately capture the features and dependencies of chemical process data, thus affecting the fault detection effect. In order to solve the above problems, a fault detection method based on multiscale feature extraction-Transformer (MFE-Transformer) is proposed in this paper. First, the linear and nonlinear features in the data are captured respectively using a multiscale feature extractor. Second, local information enhancement is achieved by capturing the local information between the data by a multilayer convolutional neural network. After that, the high coupling in the data is captured using the multi-head self-attention mechanism in Transformer to identify the complex interactions between variables. Finally, the loss contribution of easy-to-classify samples is reduced by the focal loss function, while the sample imbalance problem is solved by enhancing the number of minority class samples using sliding window data enhancement. By experimental validation on penicillin fermentation (PF) process and Tennessee Eastman (TE) process datasets, the results show that the method outperforms traditional models in terms of fault detection performance.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"4968-4988"},"PeriodicalIF":1.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038513","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
Quality-related process monitoring approach based on sparse autoencoder and comprehensive KPLS 基于稀疏自编码器和综合KPLS的质量相关过程监控方法
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-25 DOI: 10.1002/cjce.25690
Yikai Xue, Haipeng Pan, Ping Wu, Zhenyu Ye, Haiyun Zhou, Zhenquan Wu
{"title":"Quality-related process monitoring approach based on sparse autoencoder and comprehensive KPLS","authors":"Yikai Xue,&nbsp;Haipeng Pan,&nbsp;Ping Wu,&nbsp;Zhenyu Ye,&nbsp;Haiyun Zhou,&nbsp;Zhenquan Wu","doi":"10.1002/cjce.25690","DOIUrl":"https://doi.org/10.1002/cjce.25690","url":null,"abstract":"<p>The partial least squares (PLS) model is widely employed in quality-related process monitoring due to its ability to effectively establish a linear relationship between process and quality variables. To extend this capability to nonlinear scenarios, kernel partial least squares (KPLS) was introduced. However, the use of a single kernel function is often inadequate for fully capturing nonlinearity. In this paper, a novel method for quality-related process monitoring that integrates sparse autoencoders (SAE) with two KPLS models, termed SAE-CKPLS, is developed. The SAE is utilized to extract representative features from the process variables, after which two KPLS models are constructed to explore the relationship between these extracted features and residuals with the quality variables. Additionally, two Hotelling's <span></span><math>\u0000 <mrow>\u0000 <msup>\u0000 <mi>T</mi>\u0000 <mn>2</mn>\u0000 </msup>\u0000 </mrow></math> monitoring statistics are derived from the decomposed subspaces to detect quality-related faults. The capability and effectiveness of the proposed SAE-CKPLS method are demonstrated through applications to both a hot rolling mill process and the industrial Tennessee Eastman process (TEP) benchmark, with comparative analysis against related methods.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"4939-4951"},"PeriodicalIF":1.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038512","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
Multi-scale feature fusion network-based industrial process fault diagnosis method using space–time capsule and classifier optimization 基于多尺度特征融合网络的时空胶囊分类器优化工业过程故障诊断方法
IF 1.9 4区 工程技术
Canadian Journal of Chemical Engineering Pub Date : 2025-03-25 DOI: 10.1002/cjce.25682
Yue Zhao, Jianjun Bai, Hongbo Zou, Jing Feng
{"title":"Multi-scale feature fusion network-based industrial process fault diagnosis method using space–time capsule and classifier optimization","authors":"Yue Zhao,&nbsp;Jianjun Bai,&nbsp;Hongbo Zou,&nbsp;Jing Feng","doi":"10.1002/cjce.25682","DOIUrl":"https://doi.org/10.1002/cjce.25682","url":null,"abstract":"<p>This paper introduces a multi-scale feature fusion deep learning network method for industrial process fault diagnosis based on spatio-temporal capsules and classifier optimization. In the feature extraction phase, a multi-scale residual convolution network is initially employed to extract multi-scale features. Subsequently, the identified fault features are forwarded to the spatio-temporal capsule network to further extract information related to time and space. After the feature extraction is completed, we replace the traditional softmax classifier with eXtreme Gradient Boosting (XGBoost) to make the final diagnosis more efficient and faster, avoiding the long diagnosis time caused by complex models. The proposed network fully takes into account the nonlinearity, timing, and high-dimensionality of the original data. The residual network structure can solve the problem of model degradation caused by the deepening of network layers. The LSTM and capsule network structures can minimize the loss of effective feature information for features extraction and the XGBoost algorithm achieves good classification. This ‘offline training, online diagnosis’ method can avoid lengthy training and effectively improve the fault diagnosis efficiency. Our experiments on chemical engineering processes, such as the Tennessee Eastman (TE) process and industrial coking furnace, show that the proposed method significantly improves fault diagnosis accuracy.</p>","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"103 10","pages":"4989-5011"},"PeriodicalIF":1.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038511","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信