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.

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.

Amino acid digestibility of heat damaged distillers dried grains with solubles fed to pigs

The primary objective of this experiment was to determine the effects of heat treatment on the standardized ileal digestibility （SID） of amino acids （AA） in corn distillers dried grains with solubles （DDGS） fed to growing pigs. The second objective was to develop regression equations that may be used to predict the concentration of SID AA in corn DDGS. A source of corn DDGS was divided into 4 batches that were either not autoclaved or autoclaved at 130℃ for 10, 20, or 30 min. Four diets containing DDGS from each of the 4 batches were formulated with DDGS being the only source of AA and CP in the diets. A N-free diet also was formulated and used to determine the basal endogenous losses of CP and AA. Ten growing pigs （initial BW： 53.5 ＋ 3.9 kg） were surgically equipped with a T-cannula in the distal ileum and allotted to a replicated 5 x4 Youden square design with 5 diets and 4 periods in each square. The SID of CP decreased linearly （P〈 0.05） from 77.9% in non-autoclaved DDGS to 72.1, 66.1, and 68.5% in the DDGS samples that were autoclaved for 10, 20, or 30 min, respectively. The SID of lysine was quadratically reduced （P〈 0.05） from 66.8% in the non-autoclaved DDGS to 54.9, 55.3, and 51.9% in the DDGS autoclaved for 10, 20, or 30 min, respectively. The concentrations of SID Arginine, Histidine, Leucine, Lysine, Methionine, Phenylalanine, or Threonine may be best predicted by equations that include the concentration of acid detergent insoluble N in the model （r2 = 0.76, 0.68, 0.67, 0.84, 0.76, 0.73, or 0.54, respectively）. The concentrations of SID Isoleucine and Valine were predicted （r2 = 0.58 and 0.54, respectively） by the Lysine：CP ratio, whereas the concentration of SID Tryptophan was predicted （r2 = 0.70） by the analyzed concentration of Tryptophan in DDGS. In conclusion, the SID of AA is decreased as a result of heat damage and the concentration of SID AA in heat-damaged DDGS may be predicted by regression equations developed in this experiment.

Effects of dietary replacement of soybean meal with dried distillers grains with solubles on the microbiota occupying different ecological niches in the rumen of growing Hu lambs

Background:Diet has a profound impact on the rumen microbiota,and the impact can vary among the different rumen ecological niches(REN).This study investigated the effects of dietary replacement of soybean meal(SBM)with dried distillers grains with solubles(DDGS)on the rumen microbiota occupying different REN of growing Hu lambs.After a 9-week feeding trial,6 lambs from each dietary treatment(SBM vs.DDGS-based diets)were slaughtered for sample collection.The microbiota of the rumen solid,liquid,and epithelium fractions was examined using amplicon sequencing analysis of bacterial 16S rRNA gene,functional prediction,and qPCR.Results:No interaction of dietary protein source(PS)and REN were detected for virtually all the measurements made in this study.The DDGS substitution resulted in very limited influence on bacterial community structure.However,the metabolic pathways predicted from 16S rRNA gene sequences varied greatly between SBM-and DDGS-based diets.The populations of rumen total bacteria,fungi,sulfate-reducing bacteria(SRB),and methanogens were not influenced by DDGS substitution,but the population of protozoa was reduced.The bacterial communities in rumen solid(RS)and liquid(RL)were similar in taxonomic composition but were different in relative abundance of some taxa.In contrast,the bacterial composition and relative abundance of rumen epithelium(RE)were greatly distinct from those of the RS and the RL.In alignment with the bacterial relative abundance,the metabolic pathways predicted from 16S rRNA genes also varied greatly among the different REN.The populations of total bacteria,protozoa,and methanogens attached to the RE were smaller than those in the RS and RL,and the fungal population on the rumen epitheliumwas smaller than that in the RS but similar to that in the RL.On the contrary,the SRB population on the RE was greater than that in the RS and RL.Conclusions:Substitution of SBM with DDGS had greater impact to the protozoa than to the other microbes,and the microbial community structure and functions at different REN are distinct and niche-adapted.

Use of a post-production fractionation process improves the nutritional value of wheat distillers grains with solubles for young broiler chicks

Background： Post-production fractionation of wheat distillers grains with solubles（DDGS） increases their crude protein content and reduces their fiber content.This experiment was conducted to determine the effects of fractionation of wheat DDGS on apparent total tract digestibility（ATTD） and performance when fed to broiler chicks（0–21 d）.Methods： A total of 150,day-old,male broiler chicks（Ross-308 line;Lilydale Hatchery,Wynyard,Saskatchewan） weighing an average of 49.6 ± 0.8 g were assigned to one of five dietary treatments in a completely randomized design.The control diet was based on wheat and soybean meal and contained 20% regular wheat DDGS.The experimental diets contained 5,10,15 or 20% fractionated wheat DDGS added at the expense of regular wheat DDGS.Results： The ATTD of dry matter and gross energy were linearly increased（P 0.01） as the level of fractionated wheat DDGS in the diet increased.Nitrogen retention was unaffected by level of fractionated wheat DDGS（P 0.05）.Weight gain increased linearly（P = 0.05） as the level of fractionated wheat DDGS in the diet increased.Feed intake,feed conversion and mortality were unaffected by level of fractionated wheat DDGS in the diet（P 0.05）.Conclusions： Post-production fractionation of wheat DDGS improves their nutritional value by lowering their fiber content and increasing their content of crude protein and energy.These changes in chemical composition supported increased weight gain of broilers fed wheat DDGS.

Replacement of Forage Fiber Sources with Dried Distillers Grains with Solubles and Corn Germ Meal in Holstein Calf Diets

This study was carried out to determine the effect of replacement of forage fiber sources from alfalfa and Leymus chinensis with nonforage fiber sources（NFFS） from dried distillers grains with solubles and corn germ meal on calves growth, rumen development and blood parameters. 48 female and 12 male calves（（110.55±15.36） kg of body weight and 12 wk of age） were assigned randomly to four dietary treatments（15 calves/treatment） in a completely randomized design. Experimental diets were： 0% NFFS（control）, 9% NFFS（group 1）, 18% NFFS（group 2）, 27% NFFS（group 3）, and contained equivalent neutral detergent fiber and total digestible nutrients, respectively. The dry matter intake was similar among diets, averaging 3.33 kg d-1, and no differences were detected for body weight, withers height, body length and heart girth. In addition, the development of rumen, reticulum, omasum and abomasum also were similar among diets. Dry matter, crude protein, and neutral detergent fiber digestibilities increased with the increasing levels of NFFS in the experimental diets, but had no significant effect. Blood urea nitrogen, total protein and glubulin were not affected by the dietary treatment, but group 3 resulted in the highest（P〈0.05） concentrations of glucose and the lowest（P〈0.05） concentrations of triglycerides and albumin. In conclusion, dried distillers grains with solubles（DDGS） and corn germ meal（CGM） were available and alternative fiber sources for Holstein calf diets.

Amino acid digestibility in low-fat distillers dried grains with solubles fed to growing pigs

The objective of this experiment was to determine the standardized ileal digestibility（SID） of amino acids（AA） in 3sources of distillers dried grains with solubles（DDGS） with different concentrations of fat.Twelve growing barrows（initial body weight：76.1 ± 6.2 kg） were randomly allotted to a replicated 6×4 Youden square design with 6 diets and 4 periods.The fat content of the 3 sources of DDGS were 11.5,7.5,and 6.9%respectively.Diets contained 60%DDGS and fat concentration of the diets were 7.5,52,and 5.2%,respectively.Two additional diets containing the 2sources of DDGS with 75 and 6.9%fat were also formulated,and corn oil was added to these diets to increase the concentration of fat in the diets to levels that were calculated to be similar to the diet containing conventional DDGS with 11.5%fat.A N-free diet was also formulated to calculate endogenous losses of crude protein（CP） and AA from the pigs.Pigs were fed experimental diets during four 7-d periods.The first 5 d of each period were an adaptation period and ileal digesta were collected on d 6 and 7 of each period.The apparent ileal digestibililty（AID） and SID of CP and all indispensable AA,except AID Pro and SID of Trp,were greater（P 〈 0.01） in conventional DDGS than in the 2 sources of DDGS with reduced fat.Adding oil to the diets containing the 2 sources of DDGS with reduced fat did not consistently increase SID of AA.In conclusion,conventional DDGS has greater SID values for most AA compared with DDGS that contains less fat and inclusion of additional oil to diets containing low-fat DDGS does not increase AID or SID of AA.The lower AA digestibility in low-fat DDGS could not be overcome by the inclusion of additional fat to the diets.

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.

Effect of Graded Levels of Wheat Distillers Grains with Solubles on Nutrient Digestibility,Performance and Carcass Traits of Growing-Finishing Pigs Fed Diets Based on Wheat and Field Peas

This trial was conducted to determine the effects of graded levels of wheat distillers dried grains with solubles （DDGS） on nutrient digestibility, performance and carcass characteristics of pigs （21.8 to 112.3 kg） fed diets based on wheat and field peas. Forty crossbred pigs were assigned on the basis of sex and weight to one of five dietary treatments in a 5 x 2 （treatment x sex） factorial arrangement. The experimental diets were based on wheat and field peas and were formulated to contain 0, 4.86%, 9.71%, 14.57% or 19.42% wheat DDGS during the growing period and 0, 4.01%, 8.05%, 12.10% and 16.14% wheat DDGS during the finishing period. At the highest levels, ~vheat DDGS supplied 100% of the supplementary protein. The digestibility coefficient for gross energy showed a tendency towards a linear decline （P 〈 0.08 ） as the level of wheat DDGS in the diet increased while digestibility coefficients for dry matter and crude protein were unaffected （P 〉 0. 05 ） by inclusion level of wheat DDGS. During the growing period （21.8 to 60.8 kg）, weight gain of pigs fed wheat DDGS declined （P〈0.01） linearly. The impairment in growth appeared to be associated with a decrease in feed in- take which also declined linearly （P 〈 0.01 ） with increasing inclusion level of wheat DDGS. Feed conversion was unaffected by level of wheat DDGS. During the finishing period （60.8 to 112.3 kg）, and over the entire experimental period （21.8 to 112.3 kg ）, weight gain and feed conversion declined linearly as the dietary inclusion level of wheat DDGS increased. Carcass traits were generally unaffected by the inclusion of wheat DDGS with the exception of a trend towards a linear （P = 0.10） reduction in lean yield and a linear increase （ P = 0.09） in loin fat as the level of wheat DDGS in the diet increased. Overall, these results suggest that wheat DDGS are inferior to field peas as a supplementary protein source for use in swine rations.

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.

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.

Comprehensive analysis on the economy and energy demand of pressure-swing distillation and pervaporation for separating waste liquid containing multiple components

A large amount of waste liquids containing methanol/acetone/water mixtures are produced in the synthesis of methyl methacrylate(MMA).Under the advocacy of green chemical industry,it is urgent to develop an efficient,economic and energy-saving mixture separation process.Through thermodynamic azeotropic behavior and pressure sensitivity analysis,pressure-swing distillation was determined and the optimal separation pressure of each column in the process was obtained.Due to the composition of waste liquids produced were quite different in MMA production,the pressure-swing distillation separation process was designed to fully achieve the accurate waste liquids treatment.Taking the total annual cost(TAC)as the target,the sequential iteration method was used to optimize the process,and the impact of composition on economy was compared.In order to further realize the energy-saving of the separation process,the pervaporation membrane module was introduced to pretreat the waste liquid in the pressure-swing distillation.The results showed that the TAC of the coupling process was 46% higher than that of the pressure-swing distillation process,and the thermodynamic efficiency was 30% higher.This study provides waste liquid treatment technology for enterprises and analyzes its economic and energy efficiency,which has reference significance for the development of coupled separation technology.

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.

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.

Production of high-purity Mg metal from dolomite through novel molten salt electrolysis and vacuum distillation

In this study,a novel Mg production process for producing high-purity Mg metal from dolomite was developed.When the electrolysis of calcined dolomite was conducted using Cu cathode and C anode in MgF_(2)–LiF molten salt at 1083–1173 K by applying an average current of 1.42–1.46 A for 9.50–21.0 h,the current efficiency of 66.4–88.6%was obtained.The produced Mg alloys consisted of MgCu_(2)and Cu(Mg)or MgCu_(2)and CuMg_(2)phases,depending on the Mg concentration in the Mg alloy.When the electrolysis of calcined dolomite was conducted in MgF_(2)–LiF–CaF_(2)molten salt at 1083 K,the current efficiency was 40.9–71.4%,owing to undesired reactions such as electroreduction of Ca^(2+)or/and CO_(3)^(2−)ions.Meanwhile,the current efficiency increased from 40.9%to 63.2%by utilizing a Pt anode,because the occurrence of CO_(3)^(2−)ions in the molten salt was prevented.After vacuum distillation of the obtained Mg alloys at 1300 K for 10 h,Mg metal with a purity of 99.9996–99.9998%was produced.Therefore,the feasibility of this novel process for the production of high-purity Mg metal from dolomite was demonstrated.

Enrichment of nervonic acid in Acer truncatum Bunge oil by combination of two-stage molecular distillation,one-stage urea complexation and five-stage solvent crystallization

Nervonic acid is the world’s first and only potent substance that can repair damaged nerve fibers and promote nerve cell regeneration with high nutritional value.The wide variety of fatty acids in plant oils and fats with similar structures makes the large-scale separation and purification of high-purity nervonic acid very difficult.A new combined process of molecular distillation,urea inclusion and solvent crystallization was established to prepare high-purity nervonic acid with the mixed fatty acids obtained after saponification and acidification of Acer truncatum Bunge oil as raw materials.First,according to the difference in the mean free path of fatty acids,molecular distillation was used to separate and remove C16 saturated fatty acid of palmitic acid and four C18-C20 fatty acids of stearic,oleic,linoleic,and linolenic acids.The content of C16-C20 fatty acids decreased from 72.92% to 19.22% after two-stage molecular distillation processes,in which the contents of saturated fatty acid of palmitic acid decreased to about 0.5%.Then,according to the difference in carbon chain length and saturation of fatty acid,the contents of C22-C24 saturated fatty acids of tetracosanoic and docosanoic acids decreased to 0.21% and 0.07% by urea inclusion with urea/free fatty acid preparation by saponification(SPOMFs)ratio as 0.6.In addition,all saturated fatty acids were basically separated.Finally,according to the difference in the solubility of fatty acids in solvents,the C18-C20 unsaturated fatty acids of oleic,linoleic,and linolenic acids and C22 unsaturated fatty acid of erucic acid were removed by solvent crystallization.The content of C18-C20 unsaturated fatty acids decreased to less than 5% with pentanol as the solvent after the first stage solvent crystallization.The content of erucic acid decreased to 3.47% with anhydrous ethanol as the solvent after the second to fifth stage solvent crystallization.The combined process of molecular distillation,urea inclusion and low temperature crystallization innovatively adopted an efficient,simple and easy-toindustrial solvent crystallization method to separate erucic and nervonic acids,obtaining nervonic acid with purity of 96.53% and final yield of 47.99%.

Configuring topologically optimum vapor recompressed dividing-wall distillation columns to maximize operating efficiency

For dividing-wall distillation columns(DWDCs) separating a heavy-component dominated and wide boiling-point ternary(HCDWBT) mixture, a significant amount of excessive heat exists inevitably in stripping the heavy-component from the intermediate-component and it can be employed to initiate the development of vapor recompression heat pump(VRHP) assisted DWDC(VRHP-DWDC). Despite dividing wall may locate in the top, middle, and bottom, the optimum VRHP-DWDC is found to involve uniformlytwo VRHP circles. While the first one serves to compress and transform the excessive heat resulted from the separation of the heavy-component from the intermediate-component, the second one to compress and transform the overhead vapor stream of the light-component pre-heated sequentially with the condensate from the first one and the bottom product stream of the heavy-component, both releasing the temperature-elevated latent heat to the pre-fractionator's or common stripping section. The processing of two HCDWBT mixtures of benzene/toluene/o-xylene and n-pentane/n-hexane/n-heptane are selected to assess the derived optimum topological configurations of the VRHP-DWDC and their optimality is confirmed through detailed comparisons with the DWDC and two VRHP-DWDCs involving only one VRHP circle. The proposed strategy helps to tap the full potential of the VRHP-DWDC with considerably alleviated complication in process development.

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.

Decentralized Heterogeneous Federal Distillation Learning Based on Blockchain

Load forecasting is a crucial aspect of intelligent Virtual Power Plant(VPP)management and ameans of balancing the relationship between distributed power grids and traditional power grids.However,due to the continuous emergence of power consumption peaks,the power supply quality of the power grid cannot be guaranteed.Therefore,an intelligent calculation method is required to effectively predict the load,enabling better power grid dispatching and ensuring the stable operation of the power grid.This paper proposes a decentralized heterogeneous federated distillation learning algorithm(DHFDL)to promote trusted federated learning(FL)between different federates in the blockchain.The algorithm comprises two stages:common knowledge accumulation and personalized training.In the first stage,each federate on the blockchain is treated as ameta-distribution.After aggregating the knowledge of each federate circularly,the model is uploaded to the blockchain.In the second stage,other federates on the blockchain download the trained model for personalized training,both of which are based on knowledge distillation.Experimental results demonstrate that the DHFDL algorithmproposed in this paper can resist a higher proportion of malicious code compared to FedAvg and a Blockchain-based Federated Learning framework with Committee consensus(BFLC).Additionally,by combining asynchronous consensus with the FL model training process,the DHFDL training time is the shortest,and the training efficiency of decentralized FL is improved.