Rock experiment results indicate that the load/unload response ratio (LURR) of rocks expressed via strain energy may have singular or negative value after the stress in the rock reaches its maximum before rock failure...Rock experiment results indicate that the load/unload response ratio (LURR) of rocks expressed via strain energy may have singular or negative value after the stress in the rock reaches its maximum before rock failure or when the rock goes into the strain-weakening phase. The universality of this phenomenon is discussed. Expressed via strain or strain energy and the travel time of P wave, the variation form of the reciprocal of LURR during the process of rock failure preparation is derived. The results show that after a sharp decrease the reciprocal of LURR reaches its minimum when the main fracture of the rock is about to appear. This feature can be taken as an indication that the rock main fracture is impending.展开更多
Accurate capacity and State of Charge(SOC)estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric vehicles.This study examines ten machine learning architectures,Including Dee...Accurate capacity and State of Charge(SOC)estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric vehicles.This study examines ten machine learning architectures,Including Deep Belief Network(DBN),Bidirectional Recurrent Neural Network(BiDirRNN),Gated Recurrent Unit(GRU),and others using the NASA B0005 dataset of 591,458 instances.Results indicate that DBN excels in capacity estimation,achieving orders-of-magnitude lower error values and explaining over 99.97%of the predicted variable’s variance.When computational efficiency is paramount,the Deep Neural Network(DNN)offers a strong alternative,delivering near-competitive accuracy with significantly reduced prediction times.The GRU achieves the best overall performance for SOC estimation,attaining an R^(2) of 0.9999,while the BiDirRNN provides a marginally lower error at a slightly higher computational speed.In contrast,Convolutional Neural Networks(CNN)and Radial Basis Function Networks(RBFN)exhibit relatively high error rates,making them less viable for real-world battery management.Analyses of error distributions reveal that the top-performing models cluster most predictions within tight bounds,limiting the risk of overcharging or deep discharging.These findings highlight the trade-off between accuracy and computational overhead,offering valuable guidance for battery management system(BMS)designers seeking optimal performance under constrained resources.Future work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’robustness in diverse operating conditions.展开更多
In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corr...In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corresponding control strategy was proposed.The system was constituted of a pumpcontrolled part and a valve-controlled part,the pump controlled part is used to adjust the flow rate of oil source and the valve controlled part is used to complete the position tracking control of the hydraulic cylinder.Based on the system characteristics,a load flow grey prediction method was adopted in the pump controlled part to reduce the system overflow losses,and an adaptive robust control method was adopted in the valve controlled part to eliminate the effect of system nonlinearity and parametric uncertainties due to variable hydraulic parameters and system loads on the control precision.The experimental results validated that the adopted control strategy increased the system efficiency obviously with guaranteed high control accuracy.展开更多
Energy efficiency is an important aspect of increasing production capacity, minimizing environmental impact, and reducing energy usage in the petrochemical industries. However, in practice, data quality can be degrade...Energy efficiency is an important aspect of increasing production capacity, minimizing environmental impact, and reducing energy usage in the petrochemical industries. However, in practice, data quality can be degraded by measurement malfunction throughout the operation, leading to unreliable and inaccurate prediction results. Therefore, this paper presents a transfer learning fault detection and identification-energy efficiency predictor (TFDI-EEP) model formulated using long short-term memory. The model aims to predict the energy efficiency of the petrochemical process under uncertainty by using the knowledge gained from the uncertainty detection task to improve prediction performance. The transfer procedure resolves weight initialization by applying partial layer freezing before fine-tuning the additional part of the model. The performance of the proposed model is verified on a wide range of fault variations to thoroughly examine the maximum contribution of faults that the model can tolerate. The results indicate that the TFDI-EEP achieved the highest r-squared and lowest error in the testing step for both the 10% and 20% fault variation datasets compared to other conventional methods. Furthermore, the revelation of interconnection between domains shows that the proposed model can also identify strong fault-correlated features, enhancing monitoring ability and strengthening the robustness and reliability of the model observed by the number of outliers. The transfer parameter improves the prediction performance by 9.86% based on detection accuracy and achieves an r-squared greater than 0.95 on the 40% testing fault variation.展开更多
A field study was carried out to assess soil loss from ephemeral gully(EG)erosion at 6 different locations(Digil,Vimtim,Muvur,Gella,Lamorde and Madanya)around the Mubi area between April,2008 and October,2009.Each loc...A field study was carried out to assess soil loss from ephemeral gully(EG)erosion at 6 different locations(Digil,Vimtim,Muvur,Gella,Lamorde and Madanya)around the Mubi area between April,2008 and October,2009.Each location consisted of 3 watershed sites from where data was collected.EG shape,land use,and conservation practices were noted,while EG length,width,and depth were measured.Physico-chemical properties of the soils were studied in the field and laboratory.Soil loss was both measured and predicted using modeled empirical equations.Results showed that the soils are heterogeneous and lying on flat to hilly topographies with few grasses,shrubs and tree vegetations.The soils comprised of sand fractions that predominated the texture,with considerable silt and clay contents.The empirical soil loss was generally related with the measured soil loss and the predictions were widely reliable at all sites,regardless of season.The measured and empirical aggregate soil loss were more related in terms of volume of soil loss(VSL)(r^(2)=0.93)and mass of soil loss(MSL)(r^(2)=0.92),than area of soil loss(ASL)(r^(2)=0.27).The empirical estimates of VSL and MSL were consistently higher at Muvur(less vegetation)and lower at Madanya and Gella(denser vegetations)in both years.The maximum efficiency(M_(se))of the empirical equation in predicting ASL was between 1.41(Digil)and 89.07(Lamorde),while the M_(se) was higher at Madanya(2.56)and lowest at Vimtim(15.66)in terms of VSL prediction efficiencies.The M_(se) also ranged from 1.84(Madanya)to 15.74(Vimtim)in respect of MSL predictions.These results led to the recommendation that soil conservationists,farmers,private and/or government agencies should implement the empirical model in erosion studies around Mubi area.展开更多
Frequency generation in highly multimode nonlinear optical systems is inherently a complex process,giving rise to an exceedingly convoluted landscape of evolution dynamics.While predicting and controlling the global c...Frequency generation in highly multimode nonlinear optical systems is inherently a complex process,giving rise to an exceedingly convoluted landscape of evolution dynamics.While predicting and controlling the global conversion efficiencies in such nonlinear environments has long been considered impossible,here,we formally address this challenge even in scenarios involving a very large number of spatial modes.By utilizing fundamental notions from optical statistical mechanics,we develop a universal theoretical framework that effectively treats all frequency components as chemical reactants/products,capable of undergoing optical thermodynamic reactions facilitated by a variety of multi-wave mixing effects.These photon-photon reactions are governed by conservation laws that directly determine the optical temperatures and chemical potentials of the ensued chemical equilibria for each frequency species.In this context,we develop a comprehensive stoichiometric model and formally derive an expression that relates the chemical potentials to the optical stoichiometric coefficients,in a manner akin to atomic/molecular chemical reactions.This advancement unlocks new predictive capabilities that can facilitate the optimization of frequency generation in highly multimode photonic arrangements,surpassing the limitations of conventional schemes that rely exclusively on nonlinear optical dynamics.Notably,we identify a universal regime of Rayleigh-Jeans thermalization where an optical reaction at near-zero optical temperatures can promote the complete and entropically irreversible conversion of light to the fundamental mode at a target frequency.Our theoretical results are corroborated by numerical simulations in settings where second-harmonic generation,sum-frequency generation and four-wave mixing processes can manifest.展开更多
Energy efficiency in the petrochemical industry is crucial in reducing energy consumption and environmental impact.An accurate energy efficiency model will provide valuable insight for supporting operational adjustmen...Energy efficiency in the petrochemical industry is crucial in reducing energy consumption and environmental impact.An accurate energy efficiency model will provide valuable insight for supporting operational adjustment decisions.In practice,due to inconsistent sampling intervals in the petrochemical industry,the traditional approach for obtaining energy efficiency may be unreliable and difficult to handle these multirate data char-acteristics.Therefore,in this paper,a multi-channel convolutional neural network model integrating a model parameter-based transfer learning approach is proposed to improve the prediction of energy efficiency under inconsistent sampling intervals.The multi-channel structure aims to recognize a different pattern from the dataset by convolving the information along the time dimension.Concurrently,transfer learning allows the model to learn a new pattern of input after the model is fully trained.Finally,the performance for energy ef-ficiency prediction and saving analysis is validated by applying it to the vinyl chloride monomer production case study.The result shows that the proposed model outperformed traditional models and typical convolutional neural network structures in terms of accuracy and reproducibility,with an r-square of 0.97.The utilization of transfer learning prevents a significant drop in performance and enhances adaptability in model learning on real-time energy tracking.Moreover,the energy gap analysis of the prediction result identified a significant energysaving potential,which would decrease annual energy consumption by 7.25%on average and a 5,709-ton reduction in carbon dioxide emissions.展开更多
基金Key project from China Seismological Bureau (9691309020301) State Natural Sciences Foundation of China (19732060).
文摘Rock experiment results indicate that the load/unload response ratio (LURR) of rocks expressed via strain energy may have singular or negative value after the stress in the rock reaches its maximum before rock failure or when the rock goes into the strain-weakening phase. The universality of this phenomenon is discussed. Expressed via strain or strain energy and the travel time of P wave, the variation form of the reciprocal of LURR during the process of rock failure preparation is derived. The results show that after a sharp decrease the reciprocal of LURR reaches its minimum when the main fracture of the rock is about to appear. This feature can be taken as an indication that the rock main fracture is impending.
文摘Accurate capacity and State of Charge(SOC)estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric vehicles.This study examines ten machine learning architectures,Including Deep Belief Network(DBN),Bidirectional Recurrent Neural Network(BiDirRNN),Gated Recurrent Unit(GRU),and others using the NASA B0005 dataset of 591,458 instances.Results indicate that DBN excels in capacity estimation,achieving orders-of-magnitude lower error values and explaining over 99.97%of the predicted variable’s variance.When computational efficiency is paramount,the Deep Neural Network(DNN)offers a strong alternative,delivering near-competitive accuracy with significantly reduced prediction times.The GRU achieves the best overall performance for SOC estimation,attaining an R^(2) of 0.9999,while the BiDirRNN provides a marginally lower error at a slightly higher computational speed.In contrast,Convolutional Neural Networks(CNN)and Radial Basis Function Networks(RBFN)exhibit relatively high error rates,making them less viable for real-world battery management.Analyses of error distributions reveal that the top-performing models cluster most predictions within tight bounds,limiting the risk of overcharging or deep discharging.These findings highlight the trade-off between accuracy and computational overhead,offering valuable guidance for battery management system(BMS)designers seeking optimal performance under constrained resources.Future work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’robustness in diverse operating conditions.
基金Supported by Program for New Century Excellent Talents In University(NCET-12-0049)Beijing Natural Science Foundation(4132034)
文摘In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corresponding control strategy was proposed.The system was constituted of a pumpcontrolled part and a valve-controlled part,the pump controlled part is used to adjust the flow rate of oil source and the valve controlled part is used to complete the position tracking control of the hydraulic cylinder.Based on the system characteristics,a load flow grey prediction method was adopted in the pump controlled part to reduce the system overflow losses,and an adaptive robust control method was adopted in the valve controlled part to eliminate the effect of system nonlinearity and parametric uncertainties due to variable hydraulic parameters and system loads on the control precision.The experimental results validated that the adopted control strategy increased the system efficiency obviously with guaranteed high control accuracy.
基金support of the Faculty of Engineering,Kasetsart University(Grant No.65/10/CHEM/M.Eng)the Kasetsart University Research and Development Institute,and Kasetsart University.
文摘Energy efficiency is an important aspect of increasing production capacity, minimizing environmental impact, and reducing energy usage in the petrochemical industries. However, in practice, data quality can be degraded by measurement malfunction throughout the operation, leading to unreliable and inaccurate prediction results. Therefore, this paper presents a transfer learning fault detection and identification-energy efficiency predictor (TFDI-EEP) model formulated using long short-term memory. The model aims to predict the energy efficiency of the petrochemical process under uncertainty by using the knowledge gained from the uncertainty detection task to improve prediction performance. The transfer procedure resolves weight initialization by applying partial layer freezing before fine-tuning the additional part of the model. The performance of the proposed model is verified on a wide range of fault variations to thoroughly examine the maximum contribution of faults that the model can tolerate. The results indicate that the TFDI-EEP achieved the highest r-squared and lowest error in the testing step for both the 10% and 20% fault variation datasets compared to other conventional methods. Furthermore, the revelation of interconnection between domains shows that the proposed model can also identify strong fault-correlated features, enhancing monitoring ability and strengthening the robustness and reliability of the model observed by the number of outliers. The transfer parameter improves the prediction performance by 9.86% based on detection accuracy and achieves an r-squared greater than 0.95 on the 40% testing fault variation.
文摘A field study was carried out to assess soil loss from ephemeral gully(EG)erosion at 6 different locations(Digil,Vimtim,Muvur,Gella,Lamorde and Madanya)around the Mubi area between April,2008 and October,2009.Each location consisted of 3 watershed sites from where data was collected.EG shape,land use,and conservation practices were noted,while EG length,width,and depth were measured.Physico-chemical properties of the soils were studied in the field and laboratory.Soil loss was both measured and predicted using modeled empirical equations.Results showed that the soils are heterogeneous and lying on flat to hilly topographies with few grasses,shrubs and tree vegetations.The soils comprised of sand fractions that predominated the texture,with considerable silt and clay contents.The empirical soil loss was generally related with the measured soil loss and the predictions were widely reliable at all sites,regardless of season.The measured and empirical aggregate soil loss were more related in terms of volume of soil loss(VSL)(r^(2)=0.93)and mass of soil loss(MSL)(r^(2)=0.92),than area of soil loss(ASL)(r^(2)=0.27).The empirical estimates of VSL and MSL were consistently higher at Muvur(less vegetation)and lower at Madanya and Gella(denser vegetations)in both years.The maximum efficiency(M_(se))of the empirical equation in predicting ASL was between 1.41(Digil)and 89.07(Lamorde),while the M_(se) was higher at Madanya(2.56)and lowest at Vimtim(15.66)in terms of VSL prediction efficiencies.The M_(se) also ranged from 1.84(Madanya)to 15.74(Vimtim)in respect of MSL predictions.These results led to the recommendation that soil conservationists,farmers,private and/or government agencies should implement the empirical model in erosion studies around Mubi area.
基金supported by the Air Force Offce of Scientific Research(AFOSR)Multidisciplinary University Research Initiative(MURI)award on Novel light-matter interactions in topologically non-trivial Weyl semimetal structures and systems(award No.FA9550-20-1-0322)AFOSR MURI award on Programmable systems with non-Hermitian quantum dynamics(award no.FA9550-21-1-0202)+5 种基金ONR MURI award on the classical entanglement of light(award No.N00014-20-1-2789)the Army Research Offce(W911NF-23-1-0312)the Department of Energy(DE-SCo022282)W.M.Keck Foundation,the Department of Energy(DE-SCo025224),MPS Simons collaboration(Simons grant No.733682)US Air Force Research Laboratory(FA86511820019)AFRL-Applied Research Solutions(S03015)(FA8650-19-C-1692).
文摘Frequency generation in highly multimode nonlinear optical systems is inherently a complex process,giving rise to an exceedingly convoluted landscape of evolution dynamics.While predicting and controlling the global conversion efficiencies in such nonlinear environments has long been considered impossible,here,we formally address this challenge even in scenarios involving a very large number of spatial modes.By utilizing fundamental notions from optical statistical mechanics,we develop a universal theoretical framework that effectively treats all frequency components as chemical reactants/products,capable of undergoing optical thermodynamic reactions facilitated by a variety of multi-wave mixing effects.These photon-photon reactions are governed by conservation laws that directly determine the optical temperatures and chemical potentials of the ensued chemical equilibria for each frequency species.In this context,we develop a comprehensive stoichiometric model and formally derive an expression that relates the chemical potentials to the optical stoichiometric coefficients,in a manner akin to atomic/molecular chemical reactions.This advancement unlocks new predictive capabilities that can facilitate the optimization of frequency generation in highly multimode photonic arrangements,surpassing the limitations of conventional schemes that rely exclusively on nonlinear optical dynamics.Notably,we identify a universal regime of Rayleigh-Jeans thermalization where an optical reaction at near-zero optical temperatures can promote the complete and entropically irreversible conversion of light to the fundamental mode at a target frequency.Our theoretical results are corroborated by numerical simulations in settings where second-harmonic generation,sum-frequency generation and four-wave mixing processes can manifest.
文摘Energy efficiency in the petrochemical industry is crucial in reducing energy consumption and environmental impact.An accurate energy efficiency model will provide valuable insight for supporting operational adjustment decisions.In practice,due to inconsistent sampling intervals in the petrochemical industry,the traditional approach for obtaining energy efficiency may be unreliable and difficult to handle these multirate data char-acteristics.Therefore,in this paper,a multi-channel convolutional neural network model integrating a model parameter-based transfer learning approach is proposed to improve the prediction of energy efficiency under inconsistent sampling intervals.The multi-channel structure aims to recognize a different pattern from the dataset by convolving the information along the time dimension.Concurrently,transfer learning allows the model to learn a new pattern of input after the model is fully trained.Finally,the performance for energy ef-ficiency prediction and saving analysis is validated by applying it to the vinyl chloride monomer production case study.The result shows that the proposed model outperformed traditional models and typical convolutional neural network structures in terms of accuracy and reproducibility,with an r-square of 0.97.The utilization of transfer learning prevents a significant drop in performance and enhances adaptability in model learning on real-time energy tracking.Moreover,the energy gap analysis of the prediction result identified a significant energysaving potential,which would decrease annual energy consumption by 7.25%on average and a 5,709-ton reduction in carbon dioxide emissions.
