Environmental,economic and exergy analysis of separation of ternary azeotrope by variable pressure extractive distillation based on multi-objective optimization

In this work,the ternary azeotrope of tert-butyl alcohol/ethyl acetate/water is separated by extractive distillation(ED)to recover the available constituents and protect the environment.Based on the conductor like shielding model and relative volatility method,ethylene glycol was selected as the extractant in the separation process.In addition,in view of the characteristic that the relative volatility between components changes with pressure,the multi-objective optimization method based on nondominated sorting genetic algorithm II optimizes the pressure and the amount of solvent cooperatively to avoid falling into the optimal local solution.Based on the optimal process parameters,the proposed heat-integrated process can reduce the gas emissions by 29.30%.The heat-integrated ED,further coupled with the pervaporation process,can reduce gas emission by 42.36%and has the highest exergy efficiency of 47.56%.In addition,based on the heat-integrated process,the proposed two heat pump assisted heat-integrated ED processes show good economic and environmental performance.The double heat pump assisted heat-integrated ED can reduce the total annual cost by 28.78%and the gas emissions by 55.83%compared with the basis process,which has a good application prospect.This work provides a feasible approach for the separation of ternary azeotropes.

LDAS&ET-AD:Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation

Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric attack strategies are unsuitable for distillation.Additionally,the reliability of guidance from static teachers diminishes as target models become more robust.This paper proposes an AD method called Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation(LDAS&ET-AD).Firstly,a learnable distillation attack strategies generating mechanism is developed to automatically generate sample-dependent attack strategies tailored for distillation.A strategy model is introduced to produce attack strategies that enable adversarial examples(AEs)to be created in areas where the target model significantly diverges from the teachers by competing with the target model in minimizing or maximizing the AD loss.Secondly,a teacher evolution strategy is introduced to enhance the reliability and effectiveness of knowledge in improving the generalization performance of the target model.By calculating the experimentally updated target model’s validation performance on both clean samples and AEs,the impact of distillation from each training sample and AE on the target model’s generalization and robustness abilities is assessed to serve as feedback to fine-tune standard and robust teachers accordingly.Experiments evaluate the performance of LDAS&ET-AD against different adversarial attacks on the CIFAR-10 and CIFAR-100 datasets.The experimental results demonstrate that the proposed method achieves a robust precision of 45.39%and 42.63%against AutoAttack(AA)on the CIFAR-10 dataset for ResNet-18 and MobileNet-V2,respectively,marking an improvement of 2.31%and 3.49%over the baseline method.In comparison to state-of-the-art adversarial defense techniques,our method surpasses Introspective Adversarial Distillation,the top-performing method in terms of robustness under AA attack for the CIFAR-10 dataset,with enhancements of 1.40%and 1.43%for ResNet-18 and MobileNet-V2,respectively.These findings demonstrate the effectiveness of our proposed method in enhancing the robustness of deep learning networks(DNNs)against prevalent adversarial attacks when compared to other competing methods.In conclusion,LDAS&ET-AD provides reliable and informative soft labels to one of the most promising defense methods,AT,alleviating the limitations of untrusted teachers and unsuitable AEs in existing AD techniques.We hope this paper promotes the development of DNNs in real-world trust-sensitive fields and helps ensure a more secure and dependable future for artificial intelligence systems.

Energy-saving design and optimization of pressure-swing-assisted ternary heterogenous azeotropic distillations

A huge amount of energy is always consumed to separate the ternary azeotropic mixtures by distillations.The heterogeneous azeotropic distillation and the pressure-swing distillation are two kinds of effective technologies to separate heterogeneous azeotropes without entrainer addition.To give better play to the synergistic energy-saving effect of these two processes,a novel pressure-swing-assisted ternary heterogeneous azeotropic distillation(THAD)process is proposed firstly.In this process,the ternary heterogeneous azeotrope is decanted into two liquid phases before being refluxed into the azeotropic distillation column to avoid the aqueous phase remixing,and three columns'pressures are modified to decrease the flowrates of the recycle streams.Then the dividing wall column and heat integration technologies are introduced to further reduce its energy consumption,and the pressureswing-assisted ternary heterogeneous azeotropic dividing-wall column and its heat integration structure are achieved.A genetic algorithm procedure is used to optimize the proposed processes.The design results show that the proposed processes have higher energy efficiencies and lower CO_(2)emissions than the published THAD process.

Audio-Text Multimodal Speech Recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.

De-biased knowledge distillation framework based on knowledge infusion and label de-biasing techniques

Knowledge distillation,as a pivotal technique in the field of model compression,has been widely applied across various domains.However,the problem of student model performance being limited due to inherent biases in the teacher model during the distillation process still persists.To address the inherent biases in knowledge distillation,we propose a de-biased knowledge distillation framework tailored for binary classification tasks.For the pre-trained teacher model,biases in the soft labels are mitigated through knowledge infusion and label de-biasing techniques.Based on this,a de-biased distillation loss is introduced,allowing the de-biased labels to replace the soft labels as the fitting target for the student model.This approach enables the student model to learn from the corrected model information,achieving high-performance deployment on lightweight student models.Experiments conducted on multiple real-world datasets demonstrate that deep learning models compressed under the de-biased knowledge distillation framework significantly outperform traditional response-based and feature-based knowledge distillation models across various evaluation metrics,highlighting the effectiveness and superiority of the de-biased knowledge distillation framework in model compression.

Co-pyrolysis of Sewage Sludge with Distillation Residue: Kinetics Analysis via Iso-conversional Methods

This study explored the synergistic interaction of sewage sludge(SS)and distillation residue(DR)during co-pyrolysis for the optimized treatment of sewage sludge in cement kiln systems,utilizing thermogravimetric analysis(TGA)and thermogravimetric analysis with mass spectrometry(TGA-MS).The results reveal the coexisting synergistic and antagonistic effects in the co-pyrolysis of SS/DR.The synergistic effect arises from hydrogen free radicals in SS and catalytic components in ash fractions,while the antagonistic effect is mainly due to the melting of DR on the surface of SS particles during pyrolysis and the reaction of SS ash with alkali metals to form inert substances.SS/DR co-pyrolysis reduces the yielding of coke and gas while increasing tar production.This study will promote the reduction,recycling,and harmless treatment of hazardous solid waste.

Border Sensitive Knowledge Distillation for Rice Panicle Detection in UAV Images

Research on panicle detection is one of the most important aspects of paddy phenotypic analysis.A phenotyping method that uses unmanned aerial vehicles can be an excellent alternative to field-based methods.Nevertheless,it entails many other challenges,including different illuminations,panicle sizes,shape distortions,partial occlusions,and complex backgrounds.Object detection algorithms are directly affected by these factors.This work proposes a model for detecting panicles called Border Sensitive Knowledge Distillation(BSKD).It is designed to prioritize the preservation of knowledge in border areas through the use of feature distillation.Our feature-based knowledge distillation method allows us to compress the model without sacrificing its effectiveness.An imitation mask is used to distinguish panicle-related foreground features from irrelevant background features.A significant improvement in Unmanned Aerial Vehicle(UAV)images is achieved when students imitate the teacher’s features.On the UAV rice imagery dataset,the proposed BSKD model shows superior performance with 76.3%mAP,88.3%precision,90.1%recall and 92.6%F1 score.

Anomaly Detection Method Using Feature Reconstruction Based Knowledge Distillation

In recent years,anomaly detection has attracted much attention in industrial production.As traditional anomaly detection methods usually rely on direct comparison of samples,they often ignore the intrinsic relationship between samples,resulting in poor accuracy in recognizing anomalous samples.To address this problem,a knowledge distillation anomaly detection method based on feature reconstruction was proposed in this study.Knowledge distillation was performed after inverting the structure of the teacher-student network to avoid the teacher-student network sharing the same inputs and similar structure.Representability was improved by using feature splicing to unify features at different levels,and the merged features were processed and reconstructed using an improved Transformer.The experimental results show that the proposed method achieves better performance on the MVTec dataset,verifying its effectiveness and feasibility in anomaly detection tasks.This study provides a new idea to improve the accuracy and efficiency of anomaly detection.

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements on recognition accuracy and computational resources. In this paper, the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net) is proposed,where the TT-format TD(tensor decomposition) and equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable performance. Moreover, some robust network structures are developed, including the small object detection head and the dual-domain attention mechanism, which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features. Considering the imbalance of bounding box regression samples and the inaccuracy of regression geometric factors, the focal and efficient IoU(intersection of union) loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy. The proposed TDKD-Net is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the developed methods in comparison to other advanced detection algorithms, which also present high generalization and strong robustness. As a resource-efficient precise network, the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net, which provides useful insights on handling imbalanced issues and realizing domain adaptation.

Experimental and Analytical Study of a Single Effect Distillation Using Electrical Evaporator Powered by Solar Energy

The experimental and analytical investigation was conducted on a solar-powered single-effect distillation (SED). The evaporator was designed to be an electrical evaporator as opposed to the steam evaporator that existed previously. Using sun-tracking solar panels, the electrical evaporator in the designed distillation unit was powered by solar energy. Approximately 20 kWh was utilized by the small-scale distillation apparatus. This type of design is mobile, so remote areas and countries with fragile economies can utilize it on a small or large scale. Utilizing the principles of energy and mass conservation, the amount of distillate water and power required for a single unit was determined, at the low salinity (2200 PPM) with fixed boiling point temperature (Tb = 75˚C), the unit performance is approx. 98.4%. The experimental results and those derived from a mathematical model were compared, and both showed strong accord. Using engineering equation solver (EES) software, a computer program was developed for this research scenario.

Comparative Analysis: Trays versus Packed Columns in Pressure-Swing Distillation for the Separation of Tetrahydrofuran, Water and Ethanol Azeotropic Mixture

This paper delves into the comparative study of tray and packed column pressure swing distillation systems, focusing on the separation of a ternary mixture containing ethanol, tetrahydrofuran (THF), and water. The study particularly emphasizes the production of 99.5 w/w% tetrahydrofuran from the downstream product of 1,4-butanediol synthesis via diethyl maleate. Pro/II simulation software is utilized to explore various system configurations, including sieve trays, valve trays, and packed columns. Material and energy balances are performed to ascertain stream compositions and energy demands. The investigation encompasses the effects of column operating pressure on condenser and reboiler temperatures, as well as the implications of utility streams. A rigorous distillation model is employed to compare valve tray, sieve tray, and random packing (utilizing Norton Super Intalox) column designs by varying the number of trays, reflux ratio, and second distillation column pressure. Heat exchangers are integrated into the model, and their areas and utility flow rates are computed and integrated into the economic assessment. Economic analysis, guided by Net Present Value (NPV) calculations over a 20-year span, drives the selection of the most cost-effective design. Results demonstrate that while all designs are energy-efficient, the packed column system emerges as the most economical choice, offering a comprehensive framework for the separation process. Furthermore, optimal design configurations and operating conditions for both tray and packed column systems are outlined, providing valuable insights for industrial applications.

Investigation of energy-efficient heat pump assisted heterogeneous azeotropic distillation for separating of acetonitrile/ethyl acetate/n-hexane mixture

The conventional distillation is hard to accomplish the separation of acetonitrile/ethyl acetate/n-hexane mixture. Herein, a heterogeneous azeotropic distillation(HAD) without adding entrainer is proposed to separate ternary mixture. The proposed scheme is optimized via the simulated annealing algorithm and minimum total annual cost(TAC) is used as objective functions. To minimize energy consumption,heat pump is added on the basis of optimal heterogeneous azeotropic distillation and heat integration technology is used to further improve the energy recovery. The TAC, gas emission, energy consumption and exergy destruction are used to discuss the economy and environmental protection of processes.Among all the processes, the heat pump with higher preheating temperature(HPT) assisted HAD process by combining with heat integration(HAD-HPT-HI) has best performances on economic, environment,energy and exergy. Compared with conventional HAD process, the HAD-HPT-HI achieves the reductions of 52.17%, 68.86%, 65.87% and 65.46% on TAC, total energy consumption, gas emissions and exergy destruction, respectively.

Use of various MgO resources for high-purity Mg metal production through molten salt electrolysis and vacuum distillation

A green and effective electrolytic process was developed to produce high-purity Mg metal using primary and secondary resources containing Mg O as a feedstock. The electrolysis of various Mg O resources was conducted using a Cu cathode in MgF2– LiF – KCl molten salt at 1043 K by applying an average current of 1.44 A for 12.5 h. The electrolysis of calcined North Korean magnesite and seawater Mg O clinker yielded Mg alloys of MgCu2and(Cu) phases with current efficiencies of 89.6–92.4%. The electrolysis of oxidized Mg O-C refractory brick, aged ferronickel slag, and ferronickel slag yielded Mg alloys of MgCu2and(Cu) phases with current efficiencies of 59.3–92.3%. The vacuum distillation of Mg alloys obtained was conducted at 1300 K for 10 h to produce high-purity Mg metal. After vacuum distillation, Mg metal with a purity of above 99.994% was obtained. Therefore, this study demonstrates the feasibility of the production of high-purity Mg metal from various Mg O resources using a novel electrolytic process with a Cu cathode, followed by vacuum distillation.

Economy, environmental assessment and energy conservation for separation of isopropanol/diisopropyl ether/water multi-azeotropes via extractive distillation coupled pervaporation process

This wok proposed the extraction distillation coupled pervaporation(ED+PV) technology process using two different solvents to separate isopropanol(IPA) and diisopropyl ether(DIPE) from DIPE/IPA/H_(2)O ternary heterogeneous azeotropes in industrial wastewater from the synthesis of isopropanol in this study.Based on strict design specifications, simulation and sequential iteration methods are used for process design and optimization. Compared to the ethylene glycol(EG)-EG+H_(2)O process and the 1,3-propanediol(PDO)-IPA+H_(2)O process, the total annual cost(TAC) of the EG-IPA+H_(2)O process decreased by 20.76% and 7.86%(PDO). Compared to the EG-EG+H_(2)O process, the TAC of the PDO-IPA+H_(2)O process reduced 14%, but the global warming potential(GWP) and human toxicity of the PDO-IPA+H_(2)O process increased 11.3% and 4.07% respectively. Compared to the PDO-IPA+H_(2)O process, the EG-IPA+H_(2)O process saves 7.86%(TAC), 9.78%(GWP) and 9.85%(human toxicity). The ED+PV process with EG is superior to PDO in factors of TAC, energy consumption, human toxicity and environment. The EG-IPA+H_(2)O process changed the separation order of the products of the multi-azeotropic system, reduced the cost and energy conservation of the system, and enhanced the environmental protection evaluation of the process, is the best process through life cycle assessment for analyzing the economy, energy conservation, environmental assessment and human toxicity, designing cleaner products, controlling waste discharge, and promoting the chemical purification industry. This work provides a new process design and optimized separation ideas, will have a good guiding significance for the research and application separation of multi-azeotropic mixture with mixed solvents in organic wastewater from the cleaner chemical production, has been up to standard wastewater discharge process, and realized the development goal of carbon peak and carbon neutrality in the sustainable development of chemical clean industry.

Economic and entropy production evaluation of extractive distillation and solvent-assisted pressure-swing distillation by multi-objective optimization

Extractive distillation(ED)and solvent-assisted pressure-swing distillation(SA-PSD)are both special distillation processes that perform good at separating pressure-insensitive azeotropes.However,few reported studies have compared the performance of the two processes.In this paper,ED processes with N-methylpyrrolidone(NMP)and dimethlac-etamide(DMCA)as entrainer,SA-PSD process with isopropyl-alcohol(IPA)as solvent and SA-PSD process with partial heat integration(PHI-PSD)are proposed to achieve high purity separation of a mixture of cyclohexane/2-butanol system.The optimal operating conditions of the processes are obtained after optimizing with NSGA-Ⅱ algorithm when total annual cost(TAC)and the entropy production of process are set as objectives.The optimal results show that the optimal PHI-PSD process has lower TAC by 28.7% and the lower entropy production by 39.5% than the optimal SA-PSD process while the ED process with NMP as entrainer has lower TAC by 50.9% and the lower entropy production by 56.1% than the optimal SA-PSD process.The optimal results show that the ED process with NMP as entrainer has the best economic and thermodynamic efficiency among the four proposed processes in this paper.

Focus-RCNet:a lightweight recyclable waste classification algorithm based on focus and knowledge distillation

Waste pollution is a significant environmental problem worldwide.With the continuous improvement in the living standards of the population and increasing richness of the consumption structure,the amount of domestic waste generated has increased dramatically,and there is an urgent need for further treatment.The rapid development of artificial intelligence has provided an effective solution for automated waste classification.However,the high computational power and complexity of algorithms make convolutional neural networks unsuitable for real-time embedded applications.In this paper,we propose a lightweight network architecture called Focus-RCNet,designed with reference to the sandglass structure of MobileNetV2,which uses deeply separable convolution to extract features from images.The Focus module is introduced to the field of recyclable waste image classification to reduce the dimensionality of features while retaining relevant information.To make the model focus more on waste image features while keeping the number of parameters small,we introduce the SimAM attention mechanism.In addition,knowledge distillation was used to further compress the number of parameters in the model.By training and testing on the TrashNet dataset,the Focus-RCNet model not only achieved an accuracy of 92%but also showed high deployment mobility.

Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning

In this paper,to deal with the heterogeneity in federated learning(FL)systems,a knowledge distillation(KD)driven training framework for FL is proposed,where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset.To overcome the challenge of train the big teacher model in resource limited user devices,the digital twin(DT)is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources.Then,during model distillation,each user can update the parameters of its model at either the physical entity or the digital agent.The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming(MIP)problem.To solve the problem,Q-learning and optimization are jointly used,where Q-learning selects models for users and determines whether to train locally or on the server,and optimization is used to allocate resources for users based on the output of Q-learning.Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.

Modeling and Study Influence of the Temperature Parameter on Corrosion Factors in the Atmospheric Distillation Column of Crude Oil

Atmospheric distillation is the first step in separating crude oil into by-products. It uses the different boiling temperatures of the components of crude oil to separate them. But crude oil contains a large quantity of acids and corrosive gases, including sulfur compounds, naphthenic acids, carbon dioxide, oxygen, etc. However, the temperature has an important influence on the aggressiveness of the corrosion factors in the atmospheric distillation column. This paper aims to investigate the role of temperature on corrosive products in the atmospheric distillation column. The results of the developed model show that the temperature increases the corrosion rate in the atmospheric distillation column but above a certain temperature value (about 600 K), it decreases. This illustrates the dual role played by temperature in the study of corrosion within the atmospheric distillation column.

Two-Stage Edge-Side Fault Diagnosis Method Based on Double Knowledge Distillation

With the rapid development of the Internet of Things(IoT),the automation of edge-side equipment has emerged as a significant trend.The existing fault diagnosismethods have the characteristics of heavy computing and storage load,and most of them have computational redundancy,which is not suitable for deployment on edge devices with limited resources and capabilities.This paper proposes a novel two-stage edge-side fault diagnosis method based on double knowledge distillation.First,we offer a clustering-based self-knowledge distillation approach(Cluster KD),which takes the mean value of the sample diagnosis results,clusters them,and takes the clustering results as the terms of the loss function.It utilizes the correlations between faults of the same type to improve the accuracy of the teacher model,especially for fault categories with high similarity.Then,the double knowledge distillation framework uses ordinary knowledge distillation to build a lightweightmodel for edge-side deployment.We propose a two-stage edge-side fault diagnosismethod(TSM)that separates fault detection and fault diagnosis into different stages:in the first stage,a fault detection model based on a denoising auto-encoder(DAE)is adopted to achieve fast fault responses;in the second stage,a diverse convolutionmodel with variance weighting(DCMVW)is used to diagnose faults in detail,extracting features frommicro andmacro perspectives.Through comparison experiments conducted on two fault datasets,it is proven that the proposed method has high accuracy,low delays,and small computation,which is suitable for intelligent edge-side fault diagnosis.In addition,experiments show that our approach has a smooth training process and good balance.

Investigation on catalytic distillation for ethyl acetate production with different catalytic packing structures

The catalytic packing is the core component of the catalytic distillation,and how the catalyst exists in the packing has significant influence on the process.To investigate the effect of catalyst packings on the catalytic distillation process,the classical ethyl acetate reactive distillation system was utilized,and a supported catalytic packing(SCP)was prepared in comparison with the conventional tea-bag catalytic packing(TBP).Laboratory scale experiments showed that the ethyl acetate conversion of the SCP was superior to the TBP at a low catalyst loading.The effects of reaction kinetics,mass transfer performance and actual catalytic efficiency of the packings on this process were regarded as reasons and studied by combining the experiments and numerical simulation.Results suggested that the relatively immediate“in-situ separation”caused by the rapid reaction kinetics and better mass transfer performance of SCP may be a main reason for the difference of the conversion.