With the rapid development of artificial intelligence,magnetocaloric materials as well as other materials are being developed with increased efficiency and enhanced performance.However,most studies do not take phase t...With the rapid development of artificial intelligence,magnetocaloric materials as well as other materials are being developed with increased efficiency and enhanced performance.However,most studies do not take phase transitions into account,and as a result,the predictions are usually not accurate enough.In this context,we have established an explicable relationship between alloy compositions and phase transition by feature imputation.A facile machine learning is proposed to screen candidate NiMn-based Heusler alloys with desired magnetic entropy change and magnetic transition temperature with a high accuracy R^(2)≈0.98.As expected,the measured properties of prepared NiMn-based alloys,including phase transition type,magnetic entropy changes and transition temperature,are all in good agreement with the ML predictions.As well as being the first to demonstrate an explicable relationship between alloy compositions,phase transitions and magnetocaloric properties,our proposed ML model is highly predictive and interpretable,which can provide a strong theoretical foundation for identifying high-performance magnetocaloric materials in the future.展开更多
NJmat is a user-friendly,data-driven machine learning interface designed for materials design and analysis.The platform integrates advanced computational techniques,including natural language processing(NLP),large lan...NJmat is a user-friendly,data-driven machine learning interface designed for materials design and analysis.The platform integrates advanced computational techniques,including natural language processing(NLP),large language models(LLM),machine learning potentials(MLP),and graph neural networks(GNN),to facili-tate materials discovery.The platform has been applied in diverse materials research areas,including perovskite surface design,catalyst discovery,battery materials screening,structural alloy design,and molecular informatics.By automating feature selection,predictive modeling,and result interpretation,NJmat accelerates the development of high-performance materials across energy storage,conversion,and structural applications.Additionally,NJmat serves as an educational tool,allowing students and researchers to apply machine learning techniques in materials science with minimal coding expertise.Through automated feature extraction,genetic algorithms,and interpretable machine learning models,NJmat simplifies the workflow for materials informatics,bridging the gap between AI and experimental materials research.The latest version(available at https://figshare.com/articles/software/NJmatML/24607893(accessed on 01 January 2025))enhances its functionality by incorporating NJmatNLP,a module leveraging language models like MatBERT and those based on Word2Vec to support materials prediction tasks.By utilizing clustering and cosine similarity analysis with UMAP visualization,NJmat enables intuitive exploration of materials datasets.While NJmat primarily focuses on structure-property relationships and the discovery of novel chemistries,it can also assist in optimizing processing conditions when relevant parameters are included in the training data.By providing an accessible,integrated environment for machine learning-driven materials discovery,NJmat aligns with the objectives of the Materials Genome Initiative and promotes broader adoption of AI techniques in materials science.展开更多
The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communica...The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communications using a finite number of pilots.On the other hand,Deep Learning(DL)approaches have been very successful in wireless OFDM communications.However,whether they will work underwater is still a mystery.For the first time,this paper compares two categories of DL-based UWA OFDM receivers:the DataDriven(DD)method,which performs as an end-to-end black box,and the Model-Driven(MD)method,also known as the model-based data-driven method,which combines DL and expert OFDM receiver knowledge.The encoder-decoder framework and Convolutional Neural Network(CNN)structure are employed to establish the DD receiver.On the other hand,an unfolding-based Minimum Mean Square Error(MMSE)structure is adopted for the MD receiver.We analyze the characteristics of different receivers by Monte Carlo simulations under diverse communications conditions and propose a strategy for selecting a proper receiver under different communication scenarios.Field trials in the pool and sea are also conducted to verify the feasibility and advantages of the DL receivers.It is observed that DL receivers perform better than conventional receivers in terms of bit error rate.展开更多
The distillation process is an important chemical process,and the application of data-driven modelling approach has the potential to reduce model complexity compared to mechanistic modelling,thus improving the efficie...The distillation process is an important chemical process,and the application of data-driven modelling approach has the potential to reduce model complexity compared to mechanistic modelling,thus improving the efficiency of process optimization or monitoring studies.However,the distillation process is highly nonlinear and has multiple uncertainty perturbation intervals,which brings challenges to accurate data-driven modelling of distillation processes.This paper proposes a systematic data-driven modelling framework to solve these problems.Firstly,data segment variance was introduced into the K-means algorithm to form K-means data interval(KMDI)clustering in order to cluster the data into perturbed and steady state intervals for steady-state data extraction.Secondly,maximal information coefficient(MIC)was employed to calculate the nonlinear correlation between variables for removing redundant features.Finally,extreme gradient boosting(XGBoost)was integrated as the basic learner into adaptive boosting(AdaBoost)with the error threshold(ET)set to improve weights update strategy to construct the new integrated learning algorithm,XGBoost-AdaBoost-ET.The superiority of the proposed framework is verified by applying this data-driven modelling framework to a real industrial process of propylene distillation.展开更多
Metal-nitrogen-carbon(M-N-C)single-atom catalysts are widely utilized in various energy-related catalytic processes,offering a highly efficient and cost-effective catalytic system with significant potential.Recently,c...Metal-nitrogen-carbon(M-N-C)single-atom catalysts are widely utilized in various energy-related catalytic processes,offering a highly efficient and cost-effective catalytic system with significant potential.Recently,curvature-induced strain has been extensively demonstrated as a powerful tool for modulating the catalytic performance of M-N-C catalysts.However,identifying optimal strain patterns using density functional theory(DFT)is computationally intractable due to the high-dimensional search space.Here,we developed a graph neural network(GNN)integrated with an advanced topological data analysis tool-persistent homology-to predict the adsorption energy response of adsorbate under proposed curvature patterns,using nitric oxide electroreduction(NORR)as an example.Our machine learning model achieves high accuracy in predicting the adsorption energy response to curvature,with a mean absolute error(MAE)of 0.126 eV.Furthermore,we elucidate general trends in curvature-modulated adsorption energies of intermediates across various metals and coordination environments.We recommend several promising catalysts for NORR that exhibit significant potential for performance optimization via curvature modulation.This methodology can be readily extended to describe other non-bonded interactions,such as lattice strain and surface stress,providing a versatile approach for advanced catalyst design.展开更多
Background:Transrectal(TR)and transperineal(TP)biopsies are commonly used methods for diagnosing prostate cancer.However,their comparative effectiveness in conjunction with machine learning(ML)techniques remains under...Background:Transrectal(TR)and transperineal(TP)biopsies are commonly used methods for diagnosing prostate cancer.However,their comparative effectiveness in conjunction with machine learning(ML)techniques remains underexplored.This study aimed to evaluate the predictive accuracy of ML algorithms in detecting prostate cancer using data derived from TR and TP biopsies.Methods:The clinical records of patients who underwent prostate biopsy at King Saud University Medical City and King Faisal Specialist Hospital and Research Centerin Riyadh,Saudi Arabia,between 2018 and 2025 were analyzed.Data were used to train and testMLmodels,including eXtreme Gradient Boosting(XGBoost),Decision Tree,Random Forest,and Extra Trees.Results:The two datasets are comparable.The models demonstrated exceptional performance,achieving accuracies of up to 96.49%and 95.56%on TP and TR biopsy datasets,respectively.The area under the curve(AUC)values were also high,reaching 0.9988 for TP and 0.9903 for TR biopsy predictions.Conclusion:These findings highlight the potential of MLto enhance the diagnostic accuracy of prostate cancer detection irrespective of the biopsy method.However,TP biopsy data showed marginally higher accuracy,possibly because of the lower risk of contamination.While ML holds great promise for transforming prostate cancer care,further research is needed to address limitations.Collaboration between clinicians,data scientists,and researchers is crucial to ensure the clinical relevance and interpretability of ML models.展开更多
With the rapid development of artificial intelligence technology,the development of virtual reality technology has received increasing attention in various fields.Based on the difficulties in the course construction o...With the rapid development of artificial intelligence technology,the development of virtual reality technology has received increasing attention in various fields.Based on the difficulties in the course construction of“Virtual Reality Technology”,this paper adopts a questionnaire survey method to study the learning effects of students majoring in digital media technology at Guangxi University of Finance and Economics regarding the“Virtual Reality Technology”course.The research mainly involves four aspects:learning content,teaching effectiveness,learning experience,and future development needs.The research analysis in this paper not only provides strong support for the construction of a first-class course in“Virtual Reality Technology”but also offers references for the course construction of digital media technology majors in other universities.展开更多
The backwater effect caused by tributary inflow can significantly elevate the water level profile upstream of a confluence point.However,the influence of mainstream and confluence discharges on the backwater effect in...The backwater effect caused by tributary inflow can significantly elevate the water level profile upstream of a confluence point.However,the influence of mainstream and confluence discharges on the backwater effect in a river reach remains unclear.In this study,various hydrological data collected from the Jingjiang Reach of the Yangtze River in China were statistically analyzed to determine the backwater degree and range with three representative mainstream discharges.The results indicated that the backwater degree increased with mainstream discharge,and a positive relationship was observed between the runoff ratio and backwater degree at specific representative mainstream discharges.Following the operation of the Three Gorges Project,the backwater effect in the Jingjiang Reach diminished.For instance,mean backwater degrees for low,moderate,and high mainstream discharges were recorded as 0.83 m,1.61 m,and 2.41 m during the period from 1990 to 2002,whereas these values decreased to 0.30 m,0.95 m,and 2.08 m from 2009 to 2020.The backwater range extended upstream as mainstream discharge increased from 7000 m3/s to 30000 m3/s.Moreover,a random forest-based machine learning model was used to quantify the backwater effect with varying mainstream and confluence discharges,accounting for the impacts of mainstream discharge,confluence discharge,and channel degradation in the Jingjiang Reach.At the Jianli Hydrological Station,a decrease in mainstream discharge during flood seasons resulted in a 7%–15%increase in monthly mean backwater degree,while an increase in mainstream discharge during dry seasons led to a 1%–15%decrease in monthly mean backwater degree.Furthermore,increasing confluence discharge from Dongting Lake during June to July and September to November resulted in an 11%–42%increase in monthly mean backwater degree.Continuous channel degradation in the Jingjiang Reach contributed to a 6%–19%decrease in monthly mean backwater degree.Under the influence of these factors,the monthly mean backwater degree in 2017 varied from a decrease of 53%to an increase of 37%compared to corresponding values in 1991.展开更多
During the past decades, the opening China saw an unprecedented desire for foreign language learning. This English fever also involves children in primary school and even in kindergarten: For children, to create a pos...During the past decades, the opening China saw an unprecedented desire for foreign language learning. This English fever also involves children in primary school and even in kindergarten: For children, to create a positive and vivid contest during the class is an effective way of learning, since such a contest will arouse their interest and help them understand how to use what they have learned. This paper aims at discussing methods to create effective contests for children during English classroom.展开更多
CET-6 is a nationwide and standardized test to evaluate college students' English levels. Now more than 10 million college students take part in the exam every year. On August 14, 2013, the CET-4 and CET-6 examina...CET-6 is a nationwide and standardized test to evaluate college students' English levels. Now more than 10 million college students take part in the exam every year. On August 14, 2013, the CET-4 and CET-6 examination committee reformed the structure of the CET-6 papers. After that the sentence translation was changed into paragraph translation,the scores of translation section also increased to 15 points which is more difficult and more important than before. There is no doubt that CET-6will exert a great impact on the teaching and learning of College English in China. This thesis focuses on the washback effect of CET-6 translation test towards college English teaching and learning.First of all, this paper introduces the CET-6 translation test requirements, and the score requirements of translation part. The author also illustrates some significant language testing research of both domestic and foreign scholars, and explains the concept of reliability and validity. Secondly, through the survey method of interviews and questionnaire the author study the characteristics of teaching in college classroom, the effect of translation teaching, and how do students to study translation. The author makes a further research on the interaction between the translation test and the teaching and learning based on the relevant theories. At last, the author finds that the negative washback effect of the CET-6 translation test is greater than the positive one. The author reflects on the current translation teaching and learning in China, and hopes to minimize the negative effects of CET-6 translation test.展开更多
During the past few decades,mobile wireless communications have experienced four generations of technological revolution,namely from 1 G to 4 G,and the deployment of the latest 5 G networks is expected to take place i...During the past few decades,mobile wireless communications have experienced four generations of technological revolution,namely from 1 G to 4 G,and the deployment of the latest 5 G networks is expected to take place in 2019.One fundamental question is how we can push forward the development of mobile wireless communications while it has become an extremely complex and sophisticated system.We believe that the answer lies in the huge volumes of data produced by the network itself,and machine learning may become a key to exploit such information.In this paper,we elaborate why the conventional model-based paradigm,which has been widely proved useful in pre-5 G networks,can be less efficient or even less practical in the future 5 G and beyond mobile networks.Then,we explain how the data-driven paradigm,using state-of-the-art machine learning techniques,can become a promising solution.At last,we provide a typical use case of the data-driven paradigm,i.e.,proactive load balancing,in which online learning is utilized to adjust cell configurations in advance to avoid burst congestion caused by rapid traffic changes.展开更多
BACKGROUND： Conventional methods （such as occlusion therapy, fine manipulation, complementary, and alternative medicine） take effects slowly, are time and labor consuming, and have uncertain curative effects in the...BACKGROUND： Conventional methods （such as occlusion therapy, fine manipulation, complementary, and alternative medicine） take effects slowly, are time and labor consuming, and have uncertain curative effects in the treatment of amblyopia. Perceptual learning, a new method for treating amblyopia, improves the ability to process signals from the cerebral optic nerve system by specific visual stimulation and visual learning, as well as activation of the visual signal pathway utilizing brain nervous system plasticity. OBJECTIVE： This study investigated and evaluated the curative effects of perceptual learning, which can directionally increase brain plasticity, on the treatment of amblyopia in children. The relationship between curative effect and time was also analyzed. DESIGN： A self-control experiment. SETTING： Visual Science and Optometry Center, People＇s Hospital of Guangxi Zhuang Autonomous Region. PARTICIPANTS： A total of 125 amblyopic children （250 amblyopic eyes）, 73 males, 52 females, averaging （6±2） years of age, received treatment at the Visual Science and Optometry Center, People＇s Hospital of Guangxi Zhuang Autonomous Region between September 2006 and February 2007 and were recruited for this study. All children presented with no structural disease of the eyeballs. Written informed consent for therapeutic regiments was obtained from each child＇s parent. The protocol received approval from the Hospital＇s Ethics Committee. METHODS： Visual function was tested with a perceptual learning system （Research Center for Human Health and Development of Sun Yat-sen University, National Engineering Technique Research Center for Medical Care Implement） for visual noise, position noise, contour discrimination, contrast sensitivity, grating stereogram, and random-dot fusion. These tests helped to evaluate the efficiency of visual information processing of these children, and to determine the degree of defects of the optic nerve cells and the connections of visual cortical neurons. According to results of visual function tests, individualized treatment was adopted for each amblyopia patient using perceptual learning system. One course of treatment lasted one month, and treatment was performed twice every day with two training procedures （each training procedure lasted for ten minutes）. There was a ten-minute time interval between the two training procedures. The training treatment was performed in a quiet and dark environment. Visual acuity and recovery of visual function were tested every month. Original training procedure was continued or adjusted according to the results of visual function. MAIN OUTCOME MEASURES： Visual function change; relationship of curative effects and curative time. RESULTS： A total of 125 amblyopia children were included in the final analysis. The total efficiency of perceptual learning for treating amblyopia in children was 75.2%. Visual acuity began to greatly increase 3 months after treatment （P 〈 0.05）. Visual acuity was best corrected from 0.60 ± 0.23 before treatment to 0.86 ± 0.26 after treatment （P 〈 0.05）. The mean time to reach improved levels with curative effects was （2.82 ± 1.30） months, and to reach a basically cured level was （2.87 ±1.40） months. Percentage of improved visual acuity was the highest [98% （39/40）] in children that received 3 months of treatment and the lowest [55% （31/56）] in children that received 1 month of treatment （P 〈 0.05）. The percentage of basically cured levels with curative effects increased with length of learning time and was the greatest in children that received 4 months of treatment [67% （31/46）, P 〈 0.05]. CONCLUSION： Perceptual learning rapidly and remarkably improves visual function of amblyopia children; however, the curative effects are first apparent two and three months after intervention.展开更多
Recently,orthogonal time frequency space(OTFS)was presented to alleviate severe Doppler effects in high mobility scenarios.Most of the current OTFS detection schemes rely on perfect channel state information(CSI).Howe...Recently,orthogonal time frequency space(OTFS)was presented to alleviate severe Doppler effects in high mobility scenarios.Most of the current OTFS detection schemes rely on perfect channel state information(CSI).However,in real-life systems,the parameters of channels will constantly change,which are often difficult to capture and describe.In this paper,we summarize the existing research on OTFS detection based on data-driven deep learning(DL)and propose three new network structures.The presented three networks include a residual network(ResNet),a dense network(DenseNet),and a residual dense network(RDN)for OTFS detection.The detection schemes based on data-driven paradigms do not require a model that is easy to handle mathematically.Meanwhile,compared with the existing fully connected-deep neural network(FC-DNN)and standard convolutional neural network(CNN),these three new networks can alleviate the problems of gradient explosion and gradient disappearance.Through simulation,it is proved that RDN has the best performance among the three proposed schemes due to the combination of shallow and deep features.RDN can solve the issue of performance loss caused by the traditional network not fully utilizing all the hierarchical information.展开更多
Due to growing concerns regarding climate change and environmental protection,smart power generation has become essential for the economical and safe operation of both conventional thermal power plants and sustainable...Due to growing concerns regarding climate change and environmental protection,smart power generation has become essential for the economical and safe operation of both conventional thermal power plants and sustainable energy.Traditional first-principle model-based methods are becoming insufficient when faced with the ever-growing system scale and its various uncertainties.The burgeoning era of machine learning(ML)and data-driven control(DDC)techniques promises an improved alternative to these outdated methods.This paper reviews typical applications of ML and DDC at the level of monitoring,control,optimization,and fault detection of power generation systems,with a particular focus on uncovering how these methods can function in evaluating,counteracting,or withstanding the effects of the associated uncertainties.A holistic view is provided on the control techniques of smart power generation,from the regulation level to the planning level.The benefits of ML and DDC techniques are accordingly interpreted in terms of visibility,maneuverability,flexibility,profitability,and safety(abbreviated as the“5-TYs”),respectively.Finally,an outlook on future research and applications is presented.展开更多
In this paper we consider a single-machine scheduling model with deteriorating jobs and simultaneous learning, and we introduce polynomial solutions for single machine makespan minimization, total flow times minimizat...In this paper we consider a single-machine scheduling model with deteriorating jobs and simultaneous learning, and we introduce polynomial solutions for single machine makespan minimization, total flow times minimization and maximum lateness minimization corresponding to the first and second special cases of our model under some agreeable conditions. However, corresponding to the third special case of our model, we show that the optimal schedules may be different from those of the classical version for the above objective functions.展开更多
The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational per...The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ensemble methods for battery SOH estimation. The convergence of advanced machine learning with ensemble learning is anticipated to yield valuable avenues for research. Accelerated research in ensemble learning holds promising prospects for achieving more accurate and reliable battery SOH estimation under real-world conditions.展开更多
Machine learning methods have proven to be powerful in various research fields.In this paper,we show that research on radiation effects could benefit from such methods and present a machine learning-based scientific d...Machine learning methods have proven to be powerful in various research fields.In this paper,we show that research on radiation effects could benefit from such methods and present a machine learning-based scientific discovery approach.The total ionizing dose(TID)effects usually cause gain degradation of bipolar junction transistors(BJTs),leading to functional failures of bipolar integrated circuits.Currently,many experiments of TID effects on BJTs have been conducted at different laboratories worldwide,producing a large amount of experimental data which provides a wealth of information.However,it is difficult to utilize these data effectively.In this study,we proposed a new artificial neural network(ANN)approach to analyze the experimental data of TID effects on BJTs An ANN model was built and trained using data collected from different experiments.The results indicate that the proposed ANN model has advantages in capturing nonlinear correlations and predicting the data.The trained ANN model suggests that the TID hardness of a BJT tends to increase with base current I.A possible cause for this finding was analyzed and confirmed through irradiation experiments.展开更多
Clinical reports have demonstrated that the Kongsheng Zhenzhong pill （KSZZP）, a classical prescription deriving from Valuable Prescription for Emergencies, has good therapeutic effects on vascular dementia. However,...Clinical reports have demonstrated that the Kongsheng Zhenzhong pill （KSZZP）, a classical prescription deriving from Valuable Prescription for Emergencies, has good therapeutic effects on vascular dementia. However, the mechanisms that mediate its effects remain unclear. In this study, the expression of N-methyI-D-aspartate receptor 1 mRNA, the content of nitric oxide, and the concentration of calcium in neurons was determined with in situ hybridization, spectrophotometry and flow cytometry, respectively. In addition, the expressions of N-methyI-D-aspartate receptor 1, nerve growth factor protein, and glial cell line-derived neurotrophic factor protein were detected with immunohistochemistry. We found that KSZZP could significantly decrease the expression of N-methyI-D-aspartate receptor 1 mRNA and protein, the content of nitric oxide, and the concentration of calcium in neurons. KSZZP also increased the expression of nerve growth factor and glial cell line-derived neurotrophic factor protein in the hippocampus CA1 region and in the cerebral cortex. Morris water maze and passive avoidance tests verified that KSZZP ameliorated the cognitive impairments of vascular dementia rats. Moreover, the KSZZP-induced improvements in the cognitive functions of vascular dementia rats were correlated with both inhibition of N-methyl-D-aspartate-induced excitable neurotoxicity and elevation of neurotrophic factor expression.展开更多
In this paper,we present a novel data-driven design method for the human-robot interaction(HRI)system,where a given task is achieved by cooperation between the human and the robot.The presented HRI controller design i...In this paper,we present a novel data-driven design method for the human-robot interaction(HRI)system,where a given task is achieved by cooperation between the human and the robot.The presented HRI controller design is a two-level control design approach consisting of a task-oriented performance optimization design and a plant-oriented impedance controller design.The task-oriented design minimizes the human effort and guarantees the perfect task tracking in the outer-loop,while the plant-oriented achieves the desired impedance from the human to the robot manipulator end-effector in the inner-loop.Data-driven reinforcement learning techniques are used for performance optimization in the outer-loop to assign the optimal impedance parameters.In the inner-loop,a velocity-free filter is designed to avoid the requirement of end-effector velocity measurement.On this basis,an adaptive controller is designed to achieve the desired impedance of the robot manipulator in the task space.The simulation and experiment of a robot manipulator are conducted to verify the efficacy of the presented HRI design framework.展开更多
A comprehensive and precise analysis of shale gas production performance is crucial for evaluating resource potential,designing a field development plan,and making investment decisions.However,quantitative analysis ca...A comprehensive and precise analysis of shale gas production performance is crucial for evaluating resource potential,designing a field development plan,and making investment decisions.However,quantitative analysis can be challenging because production performance is dominated by the complex interaction among a series of geological and engineering factors.In fact,each factor can be viewed as a player who makes cooperative contributions to the production payoff within the constraints of physical laws and models.Inspired by the idea,we propose a hybrid data-driven analysis framework in this study,where the contributions of dominant factors are quantitatively evaluated,the productions are precisely forecasted,and the development optimization suggestions are comprehensively generated.More specifically,game theory and machine learning models are coupled to determine the dominating geological and engineering factors.The Shapley value with definite physical meaning is employed to quantitatively measure the effects of individual factors.A multi-model-fused stacked model is trained for production forecast,which provides the basis for derivative-free optimization algorithms to optimize the development plan.The complete workflow is validated with actual production data collected from the Fuling shale gas field,Sichuan Basin,China.The validation results show that the proposed procedure can draw rigorous conclusions with quantified evidence and thereby provide specific and reliable suggestions for development plan optimization.Comparing with traditional and experience-based approaches,the hybrid data-driven procedure is advanced in terms of both efficiency and accuracy.展开更多
基金supported by the National Key R&D Program of China(No.2022YFE0109500)the National Natural Science Foundation of China(Nos.52071255,52301250,52171190 and 12304027)+2 种基金the Key R&D Project of Shaanxi Province(No.2022GXLH-01-07)the Fundamental Research Funds for the Central Universities(China)the World-Class Universities(Disciplines)and the Characteristic Development Guidance Funds for the Central Universities.
文摘With the rapid development of artificial intelligence,magnetocaloric materials as well as other materials are being developed with increased efficiency and enhanced performance.However,most studies do not take phase transitions into account,and as a result,the predictions are usually not accurate enough.In this context,we have established an explicable relationship between alloy compositions and phase transition by feature imputation.A facile machine learning is proposed to screen candidate NiMn-based Heusler alloys with desired magnetic entropy change and magnetic transition temperature with a high accuracy R^(2)≈0.98.As expected,the measured properties of prepared NiMn-based alloys,including phase transition type,magnetic entropy changes and transition temperature,are all in good agreement with the ML predictions.As well as being the first to demonstrate an explicable relationship between alloy compositions,phase transitions and magnetocaloric properties,our proposed ML model is highly predictive and interpretable,which can provide a strong theoretical foundation for identifying high-performance magnetocaloric materials in the future.
基金supported by the Jiangsu Provincial Science and Technology Project Basic Research Program(Natural Science Foundation of Jiangsu Province)(No.BK20211283).
文摘NJmat is a user-friendly,data-driven machine learning interface designed for materials design and analysis.The platform integrates advanced computational techniques,including natural language processing(NLP),large language models(LLM),machine learning potentials(MLP),and graph neural networks(GNN),to facili-tate materials discovery.The platform has been applied in diverse materials research areas,including perovskite surface design,catalyst discovery,battery materials screening,structural alloy design,and molecular informatics.By automating feature selection,predictive modeling,and result interpretation,NJmat accelerates the development of high-performance materials across energy storage,conversion,and structural applications.Additionally,NJmat serves as an educational tool,allowing students and researchers to apply machine learning techniques in materials science with minimal coding expertise.Through automated feature extraction,genetic algorithms,and interpretable machine learning models,NJmat simplifies the workflow for materials informatics,bridging the gap between AI and experimental materials research.The latest version(available at https://figshare.com/articles/software/NJmatML/24607893(accessed on 01 January 2025))enhances its functionality by incorporating NJmatNLP,a module leveraging language models like MatBERT and those based on Word2Vec to support materials prediction tasks.By utilizing clustering and cosine similarity analysis with UMAP visualization,NJmat enables intuitive exploration of materials datasets.While NJmat primarily focuses on structure-property relationships and the discovery of novel chemistries,it can also assist in optimizing processing conditions when relevant parameters are included in the training data.By providing an accessible,integrated environment for machine learning-driven materials discovery,NJmat aligns with the objectives of the Materials Genome Initiative and promotes broader adoption of AI techniques in materials science.
基金funded in part by the National Natural Science Foundation of China under Grant 62401167 and 62192712in part by the Key Laboratory of Marine Environmental Survey Technology and Application,Ministry of Natural Resources,P.R.China under Grant MESTA-2023-B001in part by the Stable Supporting Fund of National Key Laboratory of Underwater Acoustic Technology under Grant JCKYS2022604SSJS007.
文摘The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communications using a finite number of pilots.On the other hand,Deep Learning(DL)approaches have been very successful in wireless OFDM communications.However,whether they will work underwater is still a mystery.For the first time,this paper compares two categories of DL-based UWA OFDM receivers:the DataDriven(DD)method,which performs as an end-to-end black box,and the Model-Driven(MD)method,also known as the model-based data-driven method,which combines DL and expert OFDM receiver knowledge.The encoder-decoder framework and Convolutional Neural Network(CNN)structure are employed to establish the DD receiver.On the other hand,an unfolding-based Minimum Mean Square Error(MMSE)structure is adopted for the MD receiver.We analyze the characteristics of different receivers by Monte Carlo simulations under diverse communications conditions and propose a strategy for selecting a proper receiver under different communication scenarios.Field trials in the pool and sea are also conducted to verify the feasibility and advantages of the DL receivers.It is observed that DL receivers perform better than conventional receivers in terms of bit error rate.
基金supported by the National Key Research and Development Program of China(2023YFB3307801)the National Natural Science Foundation of China(62394343,62373155,62073142)+3 种基金Major Science and Technology Project of Xinjiang(No.2022A01006-4)the Programme of Introducing Talents of Discipline to Universities(the 111 Project)under Grant B17017the Fundamental Research Funds for the Central Universities,Science Foundation of China University of Petroleum,Beijing(No.2462024YJRC011)the Open Research Project of the State Key Laboratory of Industrial Control Technology,China(Grant No.ICT2024B70).
文摘The distillation process is an important chemical process,and the application of data-driven modelling approach has the potential to reduce model complexity compared to mechanistic modelling,thus improving the efficiency of process optimization or monitoring studies.However,the distillation process is highly nonlinear and has multiple uncertainty perturbation intervals,which brings challenges to accurate data-driven modelling of distillation processes.This paper proposes a systematic data-driven modelling framework to solve these problems.Firstly,data segment variance was introduced into the K-means algorithm to form K-means data interval(KMDI)clustering in order to cluster the data into perturbed and steady state intervals for steady-state data extraction.Secondly,maximal information coefficient(MIC)was employed to calculate the nonlinear correlation between variables for removing redundant features.Finally,extreme gradient boosting(XGBoost)was integrated as the basic learner into adaptive boosting(AdaBoost)with the error threshold(ET)set to improve weights update strategy to construct the new integrated learning algorithm,XGBoost-AdaBoost-ET.The superiority of the proposed framework is verified by applying this data-driven modelling framework to a real industrial process of propylene distillation.
基金supported by the Natural Science Foundation of Xiamen,China(3502Z202472001)the National Natural Science Foundation of China(22402163,22021001,21925404,T2293692,and 22361132532)。
文摘Metal-nitrogen-carbon(M-N-C)single-atom catalysts are widely utilized in various energy-related catalytic processes,offering a highly efficient and cost-effective catalytic system with significant potential.Recently,curvature-induced strain has been extensively demonstrated as a powerful tool for modulating the catalytic performance of M-N-C catalysts.However,identifying optimal strain patterns using density functional theory(DFT)is computationally intractable due to the high-dimensional search space.Here,we developed a graph neural network(GNN)integrated with an advanced topological data analysis tool-persistent homology-to predict the adsorption energy response of adsorbate under proposed curvature patterns,using nitric oxide electroreduction(NORR)as an example.Our machine learning model achieves high accuracy in predicting the adsorption energy response to curvature,with a mean absolute error(MAE)of 0.126 eV.Furthermore,we elucidate general trends in curvature-modulated adsorption energies of intermediates across various metals and coordination environments.We recommend several promising catalysts for NORR that exhibit significant potential for performance optimization via curvature modulation.This methodology can be readily extended to describe other non-bonded interactions,such as lattice strain and surface stress,providing a versatile approach for advanced catalyst design.
文摘Background:Transrectal(TR)and transperineal(TP)biopsies are commonly used methods for diagnosing prostate cancer.However,their comparative effectiveness in conjunction with machine learning(ML)techniques remains underexplored.This study aimed to evaluate the predictive accuracy of ML algorithms in detecting prostate cancer using data derived from TR and TP biopsies.Methods:The clinical records of patients who underwent prostate biopsy at King Saud University Medical City and King Faisal Specialist Hospital and Research Centerin Riyadh,Saudi Arabia,between 2018 and 2025 were analyzed.Data were used to train and testMLmodels,including eXtreme Gradient Boosting(XGBoost),Decision Tree,Random Forest,and Extra Trees.Results:The two datasets are comparable.The models demonstrated exceptional performance,achieving accuracies of up to 96.49%and 95.56%on TP and TR biopsy datasets,respectively.The area under the curve(AUC)values were also high,reaching 0.9988 for TP and 0.9903 for TR biopsy predictions.Conclusion:These findings highlight the potential of MLto enhance the diagnostic accuracy of prostate cancer detection irrespective of the biopsy method.However,TP biopsy data showed marginally higher accuracy,possibly because of the lower risk of contamination.While ML holds great promise for transforming prostate cancer care,further research is needed to address limitations.Collaboration between clinicians,data scientists,and researchers is crucial to ensure the clinical relevance and interpretability of ML models.
基金Exploration and Research on the Construction of Teaching Resources for the“Virtual Reality Technology”Course in the Context of Artificial Intelligence。
文摘With the rapid development of artificial intelligence technology,the development of virtual reality technology has received increasing attention in various fields.Based on the difficulties in the course construction of“Virtual Reality Technology”,this paper adopts a questionnaire survey method to study the learning effects of students majoring in digital media technology at Guangxi University of Finance and Economics regarding the“Virtual Reality Technology”course.The research mainly involves four aspects:learning content,teaching effectiveness,learning experience,and future development needs.The research analysis in this paper not only provides strong support for the construction of a first-class course in“Virtual Reality Technology”but also offers references for the course construction of digital media technology majors in other universities.
基金supported by the National Key Research and Development Program of China(Grant No.2023YFC3209504)the National Natural Science Foundation of China(Grants No.U2040215 and 52479075)the Natural Science Foundation of Hubei Province(Grant No.2021CFA029).
文摘The backwater effect caused by tributary inflow can significantly elevate the water level profile upstream of a confluence point.However,the influence of mainstream and confluence discharges on the backwater effect in a river reach remains unclear.In this study,various hydrological data collected from the Jingjiang Reach of the Yangtze River in China were statistically analyzed to determine the backwater degree and range with three representative mainstream discharges.The results indicated that the backwater degree increased with mainstream discharge,and a positive relationship was observed between the runoff ratio and backwater degree at specific representative mainstream discharges.Following the operation of the Three Gorges Project,the backwater effect in the Jingjiang Reach diminished.For instance,mean backwater degrees for low,moderate,and high mainstream discharges were recorded as 0.83 m,1.61 m,and 2.41 m during the period from 1990 to 2002,whereas these values decreased to 0.30 m,0.95 m,and 2.08 m from 2009 to 2020.The backwater range extended upstream as mainstream discharge increased from 7000 m3/s to 30000 m3/s.Moreover,a random forest-based machine learning model was used to quantify the backwater effect with varying mainstream and confluence discharges,accounting for the impacts of mainstream discharge,confluence discharge,and channel degradation in the Jingjiang Reach.At the Jianli Hydrological Station,a decrease in mainstream discharge during flood seasons resulted in a 7%–15%increase in monthly mean backwater degree,while an increase in mainstream discharge during dry seasons led to a 1%–15%decrease in monthly mean backwater degree.Furthermore,increasing confluence discharge from Dongting Lake during June to July and September to November resulted in an 11%–42%increase in monthly mean backwater degree.Continuous channel degradation in the Jingjiang Reach contributed to a 6%–19%decrease in monthly mean backwater degree.Under the influence of these factors,the monthly mean backwater degree in 2017 varied from a decrease of 53%to an increase of 37%compared to corresponding values in 1991.
文摘During the past decades, the opening China saw an unprecedented desire for foreign language learning. This English fever also involves children in primary school and even in kindergarten: For children, to create a positive and vivid contest during the class is an effective way of learning, since such a contest will arouse their interest and help them understand how to use what they have learned. This paper aims at discussing methods to create effective contests for children during English classroom.
文摘CET-6 is a nationwide and standardized test to evaluate college students' English levels. Now more than 10 million college students take part in the exam every year. On August 14, 2013, the CET-4 and CET-6 examination committee reformed the structure of the CET-6 papers. After that the sentence translation was changed into paragraph translation,the scores of translation section also increased to 15 points which is more difficult and more important than before. There is no doubt that CET-6will exert a great impact on the teaching and learning of College English in China. This thesis focuses on the washback effect of CET-6 translation test towards college English teaching and learning.First of all, this paper introduces the CET-6 translation test requirements, and the score requirements of translation part. The author also illustrates some significant language testing research of both domestic and foreign scholars, and explains the concept of reliability and validity. Secondly, through the survey method of interviews and questionnaire the author study the characteristics of teaching in college classroom, the effect of translation teaching, and how do students to study translation. The author makes a further research on the interaction between the translation test and the teaching and learning based on the relevant theories. At last, the author finds that the negative washback effect of the CET-6 translation test is greater than the positive one. The author reflects on the current translation teaching and learning in China, and hopes to minimize the negative effects of CET-6 translation test.
基金partially supported by the National Natural Science Foundation of China(61751306,61801208,61671233)the Jiangsu Science Foundation(BK20170650)+2 种基金the Postdoctoral Science Foundation of China(BX201700118,2017M621712)the Jiangsu Postdoctoral Science Foundation(1701118B)the Fundamental Research Funds for the Central Universities(021014380094)
文摘During the past few decades,mobile wireless communications have experienced four generations of technological revolution,namely from 1 G to 4 G,and the deployment of the latest 5 G networks is expected to take place in 2019.One fundamental question is how we can push forward the development of mobile wireless communications while it has become an extremely complex and sophisticated system.We believe that the answer lies in the huge volumes of data produced by the network itself,and machine learning may become a key to exploit such information.In this paper,we elaborate why the conventional model-based paradigm,which has been widely proved useful in pre-5 G networks,can be less efficient or even less practical in the future 5 G and beyond mobile networks.Then,we explain how the data-driven paradigm,using state-of-the-art machine learning techniques,can become a promising solution.At last,we provide a typical use case of the data-driven paradigm,i.e.,proactive load balancing,in which online learning is utilized to adjust cell configurations in advance to avoid burst congestion caused by rapid traffic changes.
基金Grant from Major Scientific Research Program of Medical Treatment and Public Health of Guangxi Zhuang Autonomous Region, No.200730
文摘BACKGROUND： Conventional methods （such as occlusion therapy, fine manipulation, complementary, and alternative medicine） take effects slowly, are time and labor consuming, and have uncertain curative effects in the treatment of amblyopia. Perceptual learning, a new method for treating amblyopia, improves the ability to process signals from the cerebral optic nerve system by specific visual stimulation and visual learning, as well as activation of the visual signal pathway utilizing brain nervous system plasticity. OBJECTIVE： This study investigated and evaluated the curative effects of perceptual learning, which can directionally increase brain plasticity, on the treatment of amblyopia in children. The relationship between curative effect and time was also analyzed. DESIGN： A self-control experiment. SETTING： Visual Science and Optometry Center, People＇s Hospital of Guangxi Zhuang Autonomous Region. PARTICIPANTS： A total of 125 amblyopic children （250 amblyopic eyes）, 73 males, 52 females, averaging （6±2） years of age, received treatment at the Visual Science and Optometry Center, People＇s Hospital of Guangxi Zhuang Autonomous Region between September 2006 and February 2007 and were recruited for this study. All children presented with no structural disease of the eyeballs. Written informed consent for therapeutic regiments was obtained from each child＇s parent. The protocol received approval from the Hospital＇s Ethics Committee. METHODS： Visual function was tested with a perceptual learning system （Research Center for Human Health and Development of Sun Yat-sen University, National Engineering Technique Research Center for Medical Care Implement） for visual noise, position noise, contour discrimination, contrast sensitivity, grating stereogram, and random-dot fusion. These tests helped to evaluate the efficiency of visual information processing of these children, and to determine the degree of defects of the optic nerve cells and the connections of visual cortical neurons. According to results of visual function tests, individualized treatment was adopted for each amblyopia patient using perceptual learning system. One course of treatment lasted one month, and treatment was performed twice every day with two training procedures （each training procedure lasted for ten minutes）. There was a ten-minute time interval between the two training procedures. The training treatment was performed in a quiet and dark environment. Visual acuity and recovery of visual function were tested every month. Original training procedure was continued or adjusted according to the results of visual function. MAIN OUTCOME MEASURES： Visual function change; relationship of curative effects and curative time. RESULTS： A total of 125 amblyopia children were included in the final analysis. The total efficiency of perceptual learning for treating amblyopia in children was 75.2%. Visual acuity began to greatly increase 3 months after treatment （P 〈 0.05）. Visual acuity was best corrected from 0.60 ± 0.23 before treatment to 0.86 ± 0.26 after treatment （P 〈 0.05）. The mean time to reach improved levels with curative effects was （2.82 ± 1.30） months, and to reach a basically cured level was （2.87 ±1.40） months. Percentage of improved visual acuity was the highest [98% （39/40）] in children that received 3 months of treatment and the lowest [55% （31/56）] in children that received 1 month of treatment （P 〈 0.05）. The percentage of basically cured levels with curative effects increased with length of learning time and was the greatest in children that received 4 months of treatment [67% （31/46）, P 〈 0.05]. CONCLUSION： Perceptual learning rapidly and remarkably improves visual function of amblyopia children; however, the curative effects are first apparent two and three months after intervention.
基金supported by Beijing Natural Science Foundation(L223025)National Natural Science Foundation of China(62201067)R and D Program of Beijing Municipal Education Commission(KM202211232008)。
文摘Recently,orthogonal time frequency space(OTFS)was presented to alleviate severe Doppler effects in high mobility scenarios.Most of the current OTFS detection schemes rely on perfect channel state information(CSI).However,in real-life systems,the parameters of channels will constantly change,which are often difficult to capture and describe.In this paper,we summarize the existing research on OTFS detection based on data-driven deep learning(DL)and propose three new network structures.The presented three networks include a residual network(ResNet),a dense network(DenseNet),and a residual dense network(RDN)for OTFS detection.The detection schemes based on data-driven paradigms do not require a model that is easy to handle mathematically.Meanwhile,compared with the existing fully connected-deep neural network(FC-DNN)and standard convolutional neural network(CNN),these three new networks can alleviate the problems of gradient explosion and gradient disappearance.Through simulation,it is proved that RDN has the best performance among the three proposed schemes due to the combination of shallow and deep features.RDN can solve the issue of performance loss caused by the traditional network not fully utilizing all the hierarchical information.
文摘Due to growing concerns regarding climate change and environmental protection,smart power generation has become essential for the economical and safe operation of both conventional thermal power plants and sustainable energy.Traditional first-principle model-based methods are becoming insufficient when faced with the ever-growing system scale and its various uncertainties.The burgeoning era of machine learning(ML)and data-driven control(DDC)techniques promises an improved alternative to these outdated methods.This paper reviews typical applications of ML and DDC at the level of monitoring,control,optimization,and fault detection of power generation systems,with a particular focus on uncovering how these methods can function in evaluating,counteracting,or withstanding the effects of the associated uncertainties.A holistic view is provided on the control techniques of smart power generation,from the regulation level to the planning level.The benefits of ML and DDC techniques are accordingly interpreted in terms of visibility,maneuverability,flexibility,profitability,and safety(abbreviated as the“5-TYs”),respectively.Finally,an outlook on future research and applications is presented.
文摘In this paper we consider a single-machine scheduling model with deteriorating jobs and simultaneous learning, and we introduce polynomial solutions for single machine makespan minimization, total flow times minimization and maximum lateness minimization corresponding to the first and second special cases of our model under some agreeable conditions. However, corresponding to the third special case of our model, we show that the optimal schedules may be different from those of the classical version for the above objective functions.
基金National Natural Science Foundation of China (52075420)Fundamental Research Funds for the Central Universities (xzy022023049)National Key Research and Development Program of China (2023YFB3408600)。
文摘The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ensemble methods for battery SOH estimation. The convergence of advanced machine learning with ensemble learning is anticipated to yield valuable avenues for research. Accelerated research in ensemble learning holds promising prospects for achieving more accurate and reliable battery SOH estimation under real-world conditions.
基金supported by the National Natural Science Foundation of China (Nos. 11690040 and 11690043)。
文摘Machine learning methods have proven to be powerful in various research fields.In this paper,we show that research on radiation effects could benefit from such methods and present a machine learning-based scientific discovery approach.The total ionizing dose(TID)effects usually cause gain degradation of bipolar junction transistors(BJTs),leading to functional failures of bipolar integrated circuits.Currently,many experiments of TID effects on BJTs have been conducted at different laboratories worldwide,producing a large amount of experimental data which provides a wealth of information.However,it is difficult to utilize these data effectively.In this study,we proposed a new artificial neural network(ANN)approach to analyze the experimental data of TID effects on BJTs An ANN model was built and trained using data collected from different experiments.The results indicate that the proposed ANN model has advantages in capturing nonlinear correlations and predicting the data.The trained ANN model suggests that the TID hardness of a BJT tends to increase with base current I.A possible cause for this finding was analyzed and confirmed through irradiation experiments.
基金the National Basic Research Program of China(973Program),No.2007CB512601Science and Technology Development Plan of TCM in Shandong Province,No.2009-006Science and Technology Plan in Colleges and Universities of Shandong Province,No.J11LF60,J11LF08
文摘Clinical reports have demonstrated that the Kongsheng Zhenzhong pill （KSZZP）, a classical prescription deriving from Valuable Prescription for Emergencies, has good therapeutic effects on vascular dementia. However, the mechanisms that mediate its effects remain unclear. In this study, the expression of N-methyI-D-aspartate receptor 1 mRNA, the content of nitric oxide, and the concentration of calcium in neurons was determined with in situ hybridization, spectrophotometry and flow cytometry, respectively. In addition, the expressions of N-methyI-D-aspartate receptor 1, nerve growth factor protein, and glial cell line-derived neurotrophic factor protein were detected with immunohistochemistry. We found that KSZZP could significantly decrease the expression of N-methyI-D-aspartate receptor 1 mRNA and protein, the content of nitric oxide, and the concentration of calcium in neurons. KSZZP also increased the expression of nerve growth factor and glial cell line-derived neurotrophic factor protein in the hippocampus CA1 region and in the cerebral cortex. Morris water maze and passive avoidance tests verified that KSZZP ameliorated the cognitive impairments of vascular dementia rats. Moreover, the KSZZP-induced improvements in the cognitive functions of vascular dementia rats were correlated with both inhibition of N-methyl-D-aspartate-induced excitable neurotoxicity and elevation of neurotrophic factor expression.
基金This work was supported in part by the National Natural Science Foundation of China(61903028)the Youth Innovation Promotion Association,Chinese Academy of Sciences(2020137)+1 种基金the Lifelong Learning Machines Program from DARPA/Microsystems Technology Officethe Army Research Laboratory(W911NF-18-2-0260).
文摘In this paper,we present a novel data-driven design method for the human-robot interaction(HRI)system,where a given task is achieved by cooperation between the human and the robot.The presented HRI controller design is a two-level control design approach consisting of a task-oriented performance optimization design and a plant-oriented impedance controller design.The task-oriented design minimizes the human effort and guarantees the perfect task tracking in the outer-loop,while the plant-oriented achieves the desired impedance from the human to the robot manipulator end-effector in the inner-loop.Data-driven reinforcement learning techniques are used for performance optimization in the outer-loop to assign the optimal impedance parameters.In the inner-loop,a velocity-free filter is designed to avoid the requirement of end-effector velocity measurement.On this basis,an adaptive controller is designed to achieve the desired impedance of the robot manipulator in the task space.The simulation and experiment of a robot manipulator are conducted to verify the efficacy of the presented HRI design framework.
基金This work was supported by the National Natural Science Foundation of China(Grant No.42050104)the Science Foundation of SINOPEC Group(Grant No.P20030).
文摘A comprehensive and precise analysis of shale gas production performance is crucial for evaluating resource potential,designing a field development plan,and making investment decisions.However,quantitative analysis can be challenging because production performance is dominated by the complex interaction among a series of geological and engineering factors.In fact,each factor can be viewed as a player who makes cooperative contributions to the production payoff within the constraints of physical laws and models.Inspired by the idea,we propose a hybrid data-driven analysis framework in this study,where the contributions of dominant factors are quantitatively evaluated,the productions are precisely forecasted,and the development optimization suggestions are comprehensively generated.More specifically,game theory and machine learning models are coupled to determine the dominating geological and engineering factors.The Shapley value with definite physical meaning is employed to quantitatively measure the effects of individual factors.A multi-model-fused stacked model is trained for production forecast,which provides the basis for derivative-free optimization algorithms to optimize the development plan.The complete workflow is validated with actual production data collected from the Fuling shale gas field,Sichuan Basin,China.The validation results show that the proposed procedure can draw rigorous conclusions with quantified evidence and thereby provide specific and reliable suggestions for development plan optimization.Comparing with traditional and experience-based approaches,the hybrid data-driven procedure is advanced in terms of both efficiency and accuracy.
