•A tracking control method based on Double-DQN for an automated field robot was developed.•The developed control method was capable of tracking straight lines and polygonal lines.•The control method ...was optimized by using a reward function based on vehicle turning performance.•The rules of the tracking controller were learned in a simulation environment.
Automatically tracking paths with large curvatures smoothly and tightly is an acknowledged challenge in robotic vehicle navigation. This is particularly true for some navigation applications in which pre-defined paths such as crop rows in agricultural applications must be followed accurately. This article presents a novel path smoothing and tracking control method based on Double Deep Q-Network (Double DQN) for an automated robotic vehicle. This Double-DQN-based controller utilized a deep reinforcement learning method that scored all potential actions at the current state according to their performance index and selected the best performer as the output of the network. In this study, a path-tracking algorithm was self-developed with a deep Q-network trained by driving a rover in a simulated virtual environment. The algorithm was tested in both simulation and on a grass field to follow paths with multiple sharp turns. The performance was compared with that of the Pure-Pursuit Control (PPC) algorithm. The results showed that the Double DQN-based control dramatically reduced the settling time and the overshoot at the corner at higher forward speeds at a minor expense of slightly increased rise time and steady state error.
Chemoradiotherapy is a critical treatment for patients with locally advanced and unresectable non-small cell lung cancer (NSCLC), and it is essential to identify high-risk patients as early as ...possible owing to the high incidence of radiation pneumonitis (RP). Increasing attention is being paid to the effects of endogenous factors for RP. This study aimed to investigate the value of computed tomography (CT)-based radiomics combined with genomics in analyzing the risk of grade ≥ 2 RP in unresectable stage III NSCLC.
In this retrospective multi-center observational study, 100 patients with unresectable stage III NSCLC who were treated with chemoradiotherapy were analyzed. Radiomics features of the entire lung were extracted from pre-radiotherapy CT images. The least absolute shrinkage and selection operator algorithm was used for optimal feature selection to calculate the Rad-score for predicting grade ≥ 2 RP. Genomic DNA was extracted from formalin-fixed paraffin-embedded pretreatment biopsy tissues. Univariate and multivariate logistic regression analyses were performed to identify predictors of RP for model development. The area under the receiver operating characteristic curve was used to evaluate the predictive capacity of the model. Statistical comparisons of the area under the curve values between different models were performed using the DeLong test. Calibration and decision curves were used to demonstrate discriminatory and clinical benefit ratios, respectively.
The Rad-score was constructed from nine radiomic features to predict grade ≥ 2 RP. Multivariate analysis demonstrated that histology, Rad-score, and XRCC1 (rs25487) allele mutation were independent high-risk factors correlated with RP. The area under the curve of the integrated model combining clinical factors, radiomics, and genomics was significantly higher than that of any single model (0.827 versus 0.594, 0.738, or 0.641). Calibration and decision curve analyses confirmed the satisfactory clinical feasibility and utility of the nomogram.
Histology, Rad-score, and XRCC1 (rs25487) allele mutation could predict grade ≥ 2 RP in patients with locally advanced unresectable NSCLC after chemoradiotherapy, and the integrated model combining clinical factors, radiomics, and genomics demonstrated the best predictive efficacy.
High-quality wind power interval prediction is an effective means to ensure the economic and stable operation of the electric power system. Comparing with single-interval prediction, multi-interval ...prediction is conducive to providing more uncertainty information to decision-makers for risk quantification. Existing multi-interval prediction methods require several independent forecasting models to generate prediction intervals (PIs) at different prediction interval nominal confidence (PINC) levels, which would lead to long training time and cross-bound phenomenon. This paper constructs a novel framework to simultaneously generate multiple PIs for wind power by integrating a proposed softened multi-interval loss function into neural networks. Firstly, the effectiveness of the proposed loss function is verified via simulation data, and the suitable training method and softening factor range are found. Then, five widely used neural networks are employed with both single-interval and multi-interval loss functions to carry out multiple interval prediction on two real-world wind power datasets. The results indicate that the proposed loss function can effectively avoid the cross-bound phenomenon and decrease the mean prediction interval width of PIs. In addition, the echo state network (ESN) with the proposed loss function exhibits the best forecasting performance among the investigated models for both point prediction and interval prediction.
•Generate multiple prediction intervals for wind power simultaneously•Relieve the cross-bound phenomenon in wind power multi-interval prediction.•Soften the loss function to make it continuous and differentiable for training.•Find proper training method and softening factor for the proposed loss function.•Compare five widely-used neural networks integrating different loss functions.
Adding silica nanofiller in silicone rubber can toughen the matrix 3 orders in terms of fracture energy, which is far larger than most other nanofiller–rubber systems. To unveil the astonishing ...toughening mechanism, we employ in situ synchrotron radiation X-ray nanocomputed tomography (Nano-CT) technique with high spatial resolution (64 nm) to study the structural evolution of silica nanofiller in silicone rubber matrix at different strains. The imaging results show that silica nanofiller forms three-dimensional connected network, which couples with silicone chain network to construct a double-network structure. Stress-induced phase separation between silica nanofiller and silicone polymer chain networks is observed during tensile deformation. Unexpectedly, though the spatial position and morphology of nanofiller network changes greatly at large strains, the connectivity of nanofiller network shows negligible reduction. This indicates that nanofiller network undergoes destruction and reconstruction simultaneously, during which silica nanofiller serves as reversible high functionality cross-linker. The reversible bonding between silica nanofiller and silicone rubber or between nanofiller particles can dissipate mechanical energy effectively, which may account for the 3 orders enhancement of toughness.
Most catalysts cannot accelerate uninterrupted conversion of polysulfides, resulting in poor long-cycle and high-loading performance of lithium-sulfur (Li-S) batteries. Herein, rich p-n junction CoS
.../ZnS heterostructures embedded on N-doped carbon nanosheets are fabricated by ion-etching and vulcanization as a continuous and efficient bidirectional catalyst. The p-n junction built-in electric field in the CoS
/ZnS heterostructure not only accelerates the transformation of lithium polysulfides (LiPSs), but also promotes the diffusion and decomposition for Li
S the from CoS
to ZnS avoiding the aggregation of lithium sulfide (Li
S). Meanwhile, the heterostructure possesses a strong chemisorption ability to anchor LiPSs and superior affinity to induce homogeneous Li deposition. The assembled cell with a CoS
/ZnS@PP separator delivers a cycling stability with a capacity decay of 0.058% per cycle at 1.0 C after 1000 cycles, and a decent areal capacity of 8.97 mA h cm
at an ultrahigh sulfur mass loading of 6 mg cm
. This work reveals that the catalyst continuously and efficiently converts polysulfides via abundant built-in electric fields to promote Li-S chemistry.
A PPY/Ti3C2Tx-AE double-layer anticorrosive coating is well-designed and prepared to enhance the corrosion resistance of 304SS BPs.
Display omitted
•A PPY and Ti3C2Tx-acrylic epoxy double-layer ...coating was prepared on 304SS BPs.•The isolation by PPY avoids the galvanic corrosion after the damage of T-AE.•The double-layer coating has both anodic protection and enhanced barrier effect.
Stainless steel (SS) is a promising material for designing bipolar plates (BPs), but their further application is limited by serious corrosion problems in the acidic environment. Ti3C2Tx is expected to be used for SS BPs coatings, while galvanic corrosion will occur after the damage of Ti3C2Tx coating. Herein, a PPY/Ti3C2Tx-AE double-layer coating (DC) is well-designed and prepared on 304SS BP, which is composed of an inner electropolymerized PPY layer and an outer Ti3C2Tx-acrylic epoxy layer. When tested in 0.2 M HCl solution, the corrosion potential and corrosion current density of the DC are 38 mV and 0.00927 μA cm−2 respectively, which are superior to those of the PPY coating and the Ti3C2Tx coating. Moreover, the DC presents the best long-term stability among the three coatings. The excellent corrosion resistance is attributed to the barrier and anodic protection effects as well as the solution of galvanic corrosion. The new coating system provides a new insight into the design of DC coatings of SS BPs.
Both high-entropy materials and metal–organic frameworks (MOFs) can be used as efficient catalysts for oxygen evolution, but it remains a challenge to combine their advantages to further improve the ...oxygen evolution reaction (OER). Herein, MOFs are served as precursors to prepare the high-entropy metal sulfide (HEMS) (MnFeCoNiCu)S2 nanoparticles based on the maximized configurational entropy theory, exhibiting ultra-efficient OER performance. The strong synergistic effect among Mn, Fe, Co, Ni, and Cu builds a stable electronic structure and provides a favorable local coordination environment, which enhance the catalytic performance greatly. In addition, the appropriate doping of sulfur source contributes to modulate the electronic structure, which promotes the formation of single-phase HEMS nanoparticles with the dimeter of sub-3 nm. The (MnFeCoNiCu)S2 nanoparticles display the best OER performance (a low overpotential of 221 mV at 10 mA cm–2 in 1 M KOH solution) and good stability (remains to be 97.6% after 12 h by chronoamperometry). This work provides a potential application for high-entropy materials based on MOF precursors as OER catalysts.
Cd(II) is one of the most widespread and toxic heavy metals and seriously threatens plant growth, furthermore negatively affecting human health. For survival from this metal stress, plants always ...fight with Cd(II) toxicity by themselves or using other external factors. The effects of second metals copper (Cu(II)), zinc (Zn(II)) and calcium (Ca(II)) on the Cd(II)-affected root morphology, Cd(II) translocation and metabolic responses in Catharanthus roseus were investigated under hydroponic conditions. We found that the Cd-stressed plants displayed the browning and rot root symptom, excess H2O2 content, lipid peroxidation and Cd(II) accumulation in plants. However, the supplement with second metals largely alleviated Cd-induced toxicity, including browning and rot roots, oxidative stress and internal Cd(II) accumulation. The amended effects at metabolic and transcriptional levels involved in different second metals share either common or divergent strategies. They commonly repressed Cd uptake and promoted Cd(II) translocation from roots to shoots with divergent mechanisms. High Zn(II) could activate MTs expression in roots, while Cu(II) or Ca(II) did not under Cd(II) stress condition. The presence of Ca(II) under Cd stress condition largely initiated occurrence of lateral roots. We then grouped a metabolic diagram integrating terpenoid indole alkaloid (TIA) accumulation and TIA pathway gene expression to elucidate the metabolic response of C. roseus to Cd(II) alone or combined with second metals. The treatment with 100 Cd(II) alone largely promoted accumulation of vinblastine, vindoline, catharanthine and loganin, whereas depressed or little changed the expression levels of genes detected here, compared to 0 Cd(II) control. In the presence of Cd(II), the supplement with second metals displayed specific effect on different alkaloid. Among them, the metal Ca(II) is especially beneficial for serpentine accumulation, Zn(II) mainly promoted tabersonine production. However, the addition of Cu(II) commonly depressed accumulation of most alkaloids detected here. Generally, we presented different mechanisms by which the second metals used to alleviate Cd (II) toxicity. This plant has potential application in phytoremediation of Cd(II), due to relatively substantial accumulation of biomass, as well as secondary metabolites TIAs used as pharmaceutical materials when facing Cd stress.
•The application of Cu(II), Zn(II) or Ca(II) largely reduces Cd(II) toxicity in Catharanthus roseus.•Different mechanisms were adopted by Cu(II), Zn(II) or Ca(II) to alleviate Cd-induced damages to roots and Cd accumulation in plants.•Catharanthus roseus has potential application in phytoremediation of Cd(II), due to accumulation of biomass and TIAs.
Searching for new promising electrocatalysts with favorable architectures allowing abundant active sites and remarkable structure stability is an urgent task for the practical application of ...lithium-sulfur (Li−S) batteries. Herein, inspired by the structure of natural cactus, a new efficient and robust electrocatalyst with three-dimensional (3D) hierarchical cactus-like architecture constructed by functional zero-dimensional (0D), one-dimensional (1D), and two-dimensional (2D) components is developed. The cactus-inspired catalyst (denoted as Co@NCNT/NCNS) consists of N-doped carbon nanosheets (NCNS) and standing N-doped carbon nanotubes (NCNT) forest with embedded Co nanoparticles on the top of NCNT, which was achieved by an
in situ
catalytic growth technique. The unique structure design integrates the advantages of 0D Co accelerating catalytic redox reactions, 1D NCNT providing a fast electron pathway, and 2D NCNS assuring strong structure stability. Especially, the rich Mott-Schottky heterointerfaces between metallic Co and semiconductive NCNT can further facilitate the electron transfer, thus improving the electrocatalyst activity. Consequently, a Li−S battery with the Co@NCNT/NCNS modified separator achieves ultralong cycle life over 4000 cycles at 2 C with ultralow capacity decay of 0.016% per cycle, much superior over that of recently reported batteries. This work provides a new strategy for developing ultra-stable catalysts towards long-life Li−S batteries.
Display omitted
•MD simulation can reveal the effect of moisture on interfacial behaviors of geopolymer-aggregate interaction;•Wetting characteristics of aggregate surfaces were elucidated and ...compared.•The interfacial mechanism of geopolymer-aggregate with the participation of moisture was explained.•Mechanical behaviors of geopolymer-water-aggregate interface were investigated using peeling and shearing simulation.
The interaction between geopolymer and aggregate largely determines the mechanical properties and durability of the geopolymer concrete. The effects of moisture on interfacial behavior of geopolymer-aggregate interaction are poorly understood, especially at molecular level. Herein, molecular dynamics (MD) simulation was employed to reveal the interactive behaviors of geopolymer-aggregate interfacial system with the participation of moisture. Full atomistic models adopted for MD simulations were constructed using the sodium aluminum silicate hydrate (N-ASH) gel model and the main chemical components of the aggregates, SiO2 and CaCO3. Then the wetting characteristics of aggregate surfaces, interfacial characteristics and mechanical behaviors of the geopolymer-aggregate interfacial systems containing interfacial moisture were elucidated and compared. It is found that the SiO2 surface is hydrophobic while the CaCO3 surface exhibits hydrophilic characteristics. Interfacial moisture participates in electrostatic interaction, H-bond interaction and coordination interaction in geopolymer-aggregate interface area. Appropriate interfacial water is beneficial to the interfacial interaction of geopolymer-aggregate system, but excessive water will increase the risk of interfacial failure. The interfacial moisture affects the diffusion behavior of water molecules and Na+ ions in geopolymer to the interfacial region, and the formation of H-bonds and coordination bonds at the interface. Mechanically, with the participation of interfacial moisture, the geopolymer-SiO2 interfacial system possesses stronger tensile strength, and a greater risk of shear failure than that of geopolymer-CaCO3. The above atomic-level findings may facilitate a better design and fabrication of geopolymer concrete in engineering.