Hamed Nikravesh, Yousef Kazemzadeh, Atefeh Hasan‐Zadeh, Ali Safaei
{"title":"Microorganisms usage in enhanced oil recovery: Mechanisms, applications, benefits, and limitations","authors":"Hamed Nikravesh, Yousef Kazemzadeh, Atefeh Hasan‐Zadeh, Ali Safaei","doi":"10.1002/cjce.25476","DOIUrl":"https://doi.org/10.1002/cjce.25476","url":null,"abstract":"In today's world, where the oil and gas industry faces challenges such as declining production and the increasing need for efficient resource utilization, microbial enhanced oil recovery (MEOR) is introduced as a biological solution. This method, based on mechanisms like surfactant production, reduction of oil viscosity, and improvement of reservoir chemical properties, can increase oil recovery by 15%–20%, reduce operational costs by up to 30%, and is highly environmentally friendly. This study reviews various MEOR methods, including stimulating existing microbial activity in reservoirs or injecting microbes and nutrients. It presents successful examples of this technology in different oil fields, showing how MEOR can be a sustainable alternative to traditional methods. However, challenges such as the need for further research, control of biological processes, and advanced technology usage are also emphasized.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fuzzy averaging level control for tight product quality control","authors":"Aayush Gupta, Prakhar Srivastava, Nitin Kaistha","doi":"10.1002/cjce.25466","DOIUrl":"https://doi.org/10.1002/cjce.25466","url":null,"abstract":"This work develops a fuzzy averaging level controller (ALC) to mitigate flow variability while avoiding high and low level alarm limit breaches. Comparison with proportional (P) and proportional integral (PI) level controllers and their non‐linear variants demonstrates the fuzzy controller to be highly effective in mitigating flow transients for low and moderate size flow disturbances. The performance is comparable for large disturbances. Application of the developed fuzzy ALC to a ternary benzene‐toluene‐xylene direct split separation scheme as well as the separation section of a conventional cumene process demonstrates significantly superior product quality control due to flow transient variability mitigation. The product quality control variability is reduced by up to 1.5 times. The developed fuzzy ALC is therefore suitable for plant‐wide control applications.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"75 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Molecular simulations and deep neural networks‐based interpretable machine learning modelling of reverse adsorptive MOFs for ethane/ethylene separation","authors":"Khushboo Yadava, Shrey Srivastava, Ashutosh Yadav","doi":"10.1002/cjce.25437","DOIUrl":"https://doi.org/10.1002/cjce.25437","url":null,"abstract":"The thermal decomposition of ethane (C<jats:sub>2</jats:sub>H<jats:sub>6</jats:sub>) and the steam cracking of fossil fuels are the main sources of ethylene (C<jats:sub>2</jats:sub>H<jats:sub>4</jats:sub>). However, it usually contains 5%–9% of C<jats:sub>2</jats:sub>H<jats:sub>6</jats:sub> residue, which must be reduced to ensure its utilization during polymerization. C<jats:sub>2</jats:sub>H<jats:sub>6</jats:sub> and C<jats:sub>2</jats:sub>H<jats:sub>4</jats:sub> have comparable kinetic diameters and boiling points (C<jats:sub>2</jats:sub>H<jats:sub>6</jats:sub>: 4.44, 184.55 K; C<jats:sub>2</jats:sub>H<jats:sub>4</jats:sub>: 4.16, 169.42 K), which makes the separation process very difficult. This contribution employs a methodology that integrates machine learning (ML) with Monte Carlo simulations to evaluate the ddmof database to develop a predictive model for separating ethane (C<jats:sub>2</jats:sub>H<jats:sub>6</jats:sub>) and ethylene (C<jats:sub>2</jats:sub>H<jats:sub>4</jats:sub>). The ML model's input is the metal–organic frameworks (MOFs) chemical and structural descriptors. The grand canonical Monte Carlo (GCMC) simulations in RASPA software were carried out to calculate the equilibrium adsorption of ethane and ethylene. Different ML models such as random forest, decision tree, and deep neural network models have been tested to estimate the selectivity and ethane uptake from the MOF data being generated. Interpretable ML model using SHapley Additive exPlanations (SHAP) is developed for the better understanding of the impact of the parameters on selectivity and ethane uptake. A user‐friendly graphical user interface (<jats:styled-content style=\"fixed-case\">GUI</jats:styled-content>) is presented, allowing users to predict the ethane uptake and selectivity of MOFs simply by entering the values of chemical and structural descriptors.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel fault diagnosis framework empowered by LSTM and attention: A case study on the Tennessee Eastman process","authors":"Shuaiyu Zhao, Yiling Duan, Nitin Roy, Bin Zhang","doi":"10.1002/cjce.25460","DOIUrl":"https://doi.org/10.1002/cjce.25460","url":null,"abstract":"In the era of Industry 4.0, substantial research has been devoted to the field of fault detection and diagnosis (FDD), which plays a critical role in preventive maintenance of large chemical processes. However, the existing studies are primarily focused on few‐shot samples of process data and without considering the role of activation functions in temporal diagnostic tasks. In this paper, an end‐to‐end chemical fault diagnosis framework that combines bidirectional long short‐term memory (LSTM) with attention mechanism is proposed. In the preprocessing stage, a special sliding time window function is developed to integrate multivariate samples containing complex temporal information via operation such as subset extraction. Afterwards, the bidirectional LSTM is constructed to address dynamic and temporal relationship on longer series observation, and the attention mechanism is adopted to highlight key fault features by assigning different attention weights. A case application is performed on the enriched Tennessee Eastman process (TEP), which reduces the bias between sample statistics and larger population parameters compared to existing few‐shot sample studies. The metric evaluation experiments for six activations show that the model configured with tanh function can achieve the optimal tradeoff in chemical process tasks, providing a strong benchmark for subsequent fault diagnosis research.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"127 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmet Alp Zembat, Elifnur Gezmis‐Yavuz, Derya Y. Koseoglu‐Imer, C. Elif Cansoy
{"title":"The use of graphene nanoplatelet‐embedded PA‐6 nanofibres to remove turbidity from water","authors":"Ahmet Alp Zembat, Elifnur Gezmis‐Yavuz, Derya Y. Koseoglu‐Imer, C. Elif Cansoy","doi":"10.1002/cjce.25469","DOIUrl":"https://doi.org/10.1002/cjce.25469","url":null,"abstract":"The global challenge of providing clean water at an affordable cost has led to the need for the development of low‐cost and non‐toxic materials for the treatment and recycling of waste water. Nanofibres have emerged as a promising solution due to their superior properties. To this end, composite polyamide‐6 (PA‐6) nanofibres embedded with graphene nanoplatelets (GNPs) were prepared by electrospinning. The study investigated the effect of the ratio of GNPs, which ranged from 0.1 to 1.0 wt.%, on the mechanical properties of nanofibres and the removal of turbidity. The results showed that PA‐6 nanofibres with 0.5 wt.% GNP exhibited enhanced mechanical properties, and increasing the GNP ratio led to lower turbidity values. To the best of our knowledge, GNP‐embedded PA‐6 nanofibres have not been used for turbidity removal before, and these filter materials are promising due to their excellent fibre structure, mechanical strength, and high level of turbidity removal.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"109 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhenhua Yu, Wenjing Wang, Xueting Wang, Qingchao Jiang, Guan Wang
{"title":"Nonlinear dynamic process monitoring based on latent mapping embedding deep neural networks","authors":"Zhenhua Yu, Wenjing Wang, Xueting Wang, Qingchao Jiang, Guan Wang","doi":"10.1002/cjce.25461","DOIUrl":"https://doi.org/10.1002/cjce.25461","url":null,"abstract":"In industrial processes, complex nonlinearity and dynamics generally exist, making it challenging to achieve good results using conventional process monitoring methods. In this paper, a latent mapping embedding neural network method (LMNN) is proposed for efficient monitoring of nonlinear dynamic processes. First, a deep neural network (DNN) is employed to acquire features of state variables from nonlinear process data and expand them along with the input to a new feature subspace. Second, a latent mapping (LM) method is used to map the high‐dimensional feature subspace to a low‐dimensional subspace that includes the most beneficial time series information. Then the entire neural network and regression parameters are obtained through an end‐to‐end learning manner, through which the nonlinearity and process dynamics are well characterized. Subsequently, prediction error‐based residual is generated and the monitoring model is established. The performance of the proposed method is verified through a simulation of penicillin production process and an actual fermentation process of penicillin. Comparisons with state‐of‐the‐art methods are carried out, and results validate the effectiveness and superiority of the proposed method.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stacked dynamic target regularization enhanced autoencoder for soft sensor in industrial processes","authors":"Xiaoping Guo, Xiaofeng Zhao, Yuan Li","doi":"10.1002/cjce.25447","DOIUrl":"https://doi.org/10.1002/cjce.25447","url":null,"abstract":"Stacked autoencoders (SAEs) have great potential in developing soft sensors due to their excellent feature extraction capabilities. However, the pre‐training stage of SAE is unsupervised and some important information related to target variables may be discarded. Meanwhile, as the depth of the network increases, reconstruction errors continue to accumulate, resulting in incomplete feature representations of the original input. In addition, the dynamic nature of the data affects the predictive results of the model. To address these issues, the stacked dynamic target regularization enhanced autoencoder (SDTR‐EAE) method is proposed, which adds the DTR and the original input information layer by layer to enhance the feature extraction. To adapt to the dynamic changes in data and extract target‐related features, entropy weight grey relational analysis (EW‐GRA) is used as the DTR term to constrain the weight matrix and suppress irrelevant features. To reduce the accumulation of information loss during the reconstruction, an information enhancement layer is introduced, where the original inputs and the information of the hidden layers of previous DTR‐EAE units are added to the follow‐up DTR‐EAE unit. Finally, in the regression process, the DTR term is used again to fully utilize depth features for quality prediction and prevent overfitting. Experimental verifications using the debutanizer column and thermal power plant are conducted to validate the effectiveness of the proposed modelling method.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"169 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Pressure loss in packed beds of multicomponent mixtures of flat particles with particle overlap, including random chips","authors":"Evangelina Schonfeldt, William L. H. Hallett","doi":"10.1002/cjce.25471","DOIUrl":"https://doi.org/10.1002/cjce.25471","url":null,"abstract":"wPressure loss measurements are presented for packed beds of multi‐component mixtures of thin angular parallelepipeds and of random wood chips for a Reynolds number range of 50 to 500. For flat particles like these, the degree to which the particles overlap is an essential factor in pressure loss, and this was measured using two different methods, including a novel technique involving progressive dismantling and photography of the bed. The experimental friction factors were found to be well represented by the Nemec and Levec pressure loss correlation, an Ergun‐type equation with an explicit dependence of the parameters on particle sphericity, with the equation expanded to include the effects of particle overlap and of packing anomalies at the wall. The friction losses of the mixtures were found to be somewhat higher than those of the individual component particles, requiring a minor change in the correlation parameters. Estimates of the tortuosity of the bed channels showed that the greater losses of the mixtures correspond to an increase in tortuosity.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"88 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Three‐layer deep learning network random trees for fault detection in chemical production process","authors":"Ming Lu, Zhen Gao, Ying Zou, Zuguo Chen, Pei Li","doi":"10.1002/cjce.25465","DOIUrl":"https://doi.org/10.1002/cjce.25465","url":null,"abstract":"With the development of technology, the chemical production process is becoming increasingly complex and large‐scale, making fault detection particularly important. However, current detection methods struggle to address the complexities of large‐scale production processes. In this paper, we integrate the strengths of deep learning and machine learning technologies, combining the advantages of bidirectional long‐ and short‐term memory neural networks, fully connected neural networks, and the extra trees algorithm to propose a novel fault detection model named three‐layer deep learning network random trees (TDLN‐trees). First, the deep learning component extracts temporal features from industrial data, combining and transforming them into a higher‐level data representation. Second, the machine learning component processes and classifies the features extracted in the first step. An experimental analysis based on the Tennessee Eastman process verifies the superiority of the proposed method.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mojtaba Mohammadi, Mohammadreza Nofar, Pierre J. Carreau
{"title":"Properties of blends of amorphous and semicrystalline PLAs containing multiwalled carbon nanotubes","authors":"Mojtaba Mohammadi, Mohammadreza Nofar, Pierre J. Carreau","doi":"10.1002/cjce.25463","DOIUrl":"https://doi.org/10.1002/cjce.25463","url":null,"abstract":"Blend nanocomposites of amorphous polylactide (aPLA) and semicrystalline PLA (scPLA)‐multiwalled carbon nanotubes (MWCNTs) were prepared by a twin‐screw extruder below the melting temperature of the scPLA. The maximum weight percent of MWCNTs in the blends was 0.9 wt.%. The extrudates were either pelletized immediately or after drawing at a drawing ratio of about 10. According to small amplitude oscillatory shear rheological analysis, the rheological properties of the aPLA/scPLA (85/15 wt.%) drawn sample were significantly increased compared to the undrawn samples. With the presence of MWCNTs, more crystallites could develop in the scPLA, and the electrical conductivity of the aPLA/scPLA nanocomposites was reduced due to the encapsulation of MWCNTs within the crystallites of scPLA. Increasing the temperature during compression moulding to 190°C, which is above the melting temperature of the scPLA, effectively removed this obstacle and the electrical conductivity was increased by a factor of up to 10<jats:sup>6</jats:sup> compared to the samples moulded at 150°C.","PeriodicalId":501204,"journal":{"name":"The Canadian Journal of Chemical Engineering","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}