The application of Large Language Models (LLMs) in the field of robotics has gained widespread attention. Due to their powerful code generation and contextual understanding capabilities, these models can generate rewa...
详细信息
This article addresses the sensor fault estimation and the fault-tolerant control (FTC) problem of the networked control systems (NCSs) with external disturbances and network-induced delay. Firstly, the sensor fault s...
详细信息
Pre-synchronization is necessary for the grid-forming (GFM) inverters to integrate into the grid. This article presents a sliding mode control (SMC)-based pre-synchronization strategy for virtual oscillator-controlled...
详细信息
Soil extracellular electron transfer(EET)is a pivotal biological process within the realm of ***,EET suffers from a lack of predictive ***,an intricately crafted machine learning model has been developed for the purpo...
详细信息
Soil extracellular electron transfer(EET)is a pivotal biological process within the realm of ***,EET suffers from a lack of predictive ***,an intricately crafted machine learning model has been developed for the purpose of predicting soil EET by using the physicochemical properties of soil as independent input variables and the EET capabilities in terms of current density(j_(max))and Coulombic charge(C_(out))as dependent output *** autoencoder ensemble stacking(AES)model was developed to address the aforementioned issue by integrating support vector machine,multilayer perceptron,extreme gradient boosting,and light gradient boosting machine algorithms as the stacking *** 10-fold crossvalidation,the AES model exhibited notable improvements in predicting j_(max)and C_(out),with average test R^(2)values of 0.83 and 0.84,respectively,surpassing those of single machine learning(ML)models and the basic ensemble *** utilizing partial correlation plots(PDPs),Shapley Additive explanations(SHAP)values,and SHAP decision plots,we quantitatively explained the impact and contribution of the input molecules on the AES model’s predictions of j_(max)and C_(out).In the context of the SHAP method for the AES model,total carbon(TC)was identified as the most correlated descriptor for j_(max),while total organic carbon(TOC)stood out as the most relevant descriptor for C_(out).In the prediction tasks of j_(max)and C_(out)within the AES model,employing a multitask ML approach allowed the model to benefit from the shared information of input variables,thereby enhancing its overall *** study provides a feasible tool for the prediction of soil EET from soil physiochemical properties and an advanced understanding of the relationship between soil physiochemical properties and EET capability.
Three sets of MXene(Ti_(3)C_(2)T_(x))@nano-Fe_(1)Co_(0.8)Ni_(1)composites with 15,45,and 90 mg MXene were prepared by in-situ liquid-phase deposition to effectively investigate the impact of the relationship between M...
详细信息
Three sets of MXene(Ti_(3)C_(2)T_(x))@nano-Fe_(1)Co_(0.8)Ni_(1)composites with 15,45,and 90 mg MXene were prepared by in-situ liquid-phase deposition to effectively investigate the impact of the relationship between MXene(Ti_(3)C_(2)T_(x))and nano-Fe_(1)Co_(0.8)Ni_(1)magnetic particles on the electromagnetic absorption properties of the *** microstructure,static magnetic properties,and electromag-netic absorption performance of these composites were *** indicate that the MXene@nano-Fe_(1)Co_(0.8)Ni_(1)composites were primarily composed of face-centered cubic crystal structure particles and MXene,with spherical Fe_(1)Co_(0.8)Ni_(1)particles uniformly distrib-uted on the surface of the multilayered *** alloy particles had an average particle size of approximately 100 nm and exhibited good dispersion without noticeable particle *** the increase in MXene content,the specific saturation magnetic and coer-civity of the composite initially decreased and then increased,displaying typical soft magnetic *** with those of the Fe_(1)Co_(0.8)Ni_(1)magnetic alloy particles alone,MXene addition caused an increasing trend in the real and imaginary parts of the dielectric constant of the ***,the real and imaginary parts of the magnetic permeability exhibit decreasing *** the in-crease in MXene addition,the material attenuation constant increased and the impedance matching *** minimum reflection loss increased,and the maximum effective absorption bandwidth *** the MXene addition was 90 mg,the composite exhib-ited a minimum reflection loss of-46.9 dB with a sample thickness of 1.1 mm and a maximum effective absorption bandwidth of 3.60 GHz with a sample thickness of 1.0 *** effective absorption bandwidth of the composites and their corresponding thicknesses showed a decreasing trend with the increase in MXene addition,reducing by 50%from 1.5 mm without MXene addition to 1 mm with 9
In DC microgrids, the accurate estimation of key parameters will provide pivotal information for power quality evaluation, stability analysis, and distributed control, etc. This paper proposes a novel method to estima...
详细信息
To enhance the task execution capability of home service robots and address the issues of uncontrolled output quality of LLMs and the inability to update information autonomously, we propose the Hierarchical Action Se...
详细信息
Lithium-ion batteries often experience overcharge due to battery management system failure or battery pack inconsistencies, which lead to serious safety accidents. Therefore, an effective overcharge warning method is ...
详细信息
Considering the nonlinearity, large fluctuations, and rich frequency components of industrial loads, this paper proposes a short-term industrial load forecasting model. The model is based on Variational Mode Decomposi...
详细信息
Human-Computer Interaction (HRI) is crucial in robotics. This article introduces a new method for human-machine interaction on robotic arms using a drag teaching approach. By analyzing the kinematics and dynamics of t...
详细信息
暂无评论