Multi-feature sparse representation based on adaptive graph constraint for cropland delineation.

Cropland delineation is the basis of agricultural resource surveys and many algorithms for plot identification have been studied. However, there is still a vacancy in SRC for cropland delineation with the high-dimensional data extracted from UAV RGB photographs. In order to address this problem, a new sparsity-based classification algorithm is proposed. Firstly, the multi-feature association sparse model is designed by extracting the multi-feature of UAV RGB photographs. Next, the samples with similar characteristics are hunted with the breadth-first principle to construct a shape-adaptive window for each test. Finally, an algorithm, multi-feature sparse representation based on adaptive graph constraint (AMFSR), is obtained by solving the optimal objective iteratively. Experimental results show that the overall accuracy (OA) of AMFSR reaches 92.3546% and the Kappa is greater than 0.8. Furthermore, experiments have demonstrated that the model also has a generalization ability.

Online lithium-ion battery intelligent perception for thermal fault detection and localization.

-Equipping lithium-ion batteries with a reasonable thermal fault diagnosis can avoid thermal runaway and ensure the safe and reliable operation of the batteries. This research built a lithium-ion battery thermal fault diagnosis model that optimized the original mask region-based convolutional neural network based on the battery dataset in both parameters and structure. The model processes the thermal images of the battery surface, identifies problematic batteries, and locates the problematic regions. A backbone network is used to process the battery thermal images and extract feature information. Through the RPN network, the thermal feature is classified and regressed, and the Mask branch is used to ultimately determine the faulty battery's location. Additionally, we have optimized the original mask region-based convolutional neural network based on the battery dataset in both parameters and structure. The improved LBIP-V2 performs better than LBIP-V1 in most cases. We tested the performance of LBIP on the single-cell battery dataset, the 1P3S battery pack dataset, and the flattened 1P3S battery pack dataset. The results show that the recognition accuracy of LBIP exceeded 95 %. At the same time, we simulated the failure of the 1P3S battery pack within 0-15 min and tested the effectiveness of LBIP in real-time battery fault diagnosis. The results indicate that LBIP can effectively respond to online faults with a confidence level of over 98 %.

Experimental and Numerical Simulation Studies on V-Shaped Bending of Aluminum/CFRP Laminates.

With the increasing requirements of automotive lightweighting, metal/CFRP laminates are increasingly used. In this paper, Al/CFRP laminates were prepared using an integrated hot press curing method, and the optimum curing conditions were determined using the single-lap shear test at 130 °C for 45 min. The effects of fiber lay-up, forming speed, and metal layer thickness on bending springback were investigated using the V-shaped bending test and Abaqus finite element analysis method. The results show that fiber lay-up has an important influence on springback. Among the five different fiber lay-ups (0° unidirectional, 90° unidirectional, 0° orthotropic, 90° orthotropic, and 45° orthotropic), the 45° orthotropic lay-up had the lowest springback rate of 1.11%. Increasing the thickness of the sheet metal can significantly reduce the resilience rate. As the sheet thickness increased from 2 mm to 3 mm, the springback of the 90° unidirectional lay-up decreased by 43%. Springback was not sensitive to forming speed, and the difference in springback was within 1% at different forming speeds. The damage behavior of the forming process was analyzed using the three-dimensional Hashin damage law with the Vumat subroutine and microscopic analysis. Fiber and resin damage under 45° orthotropic lay-up conditions was relatively small compared to fiber damage under 0° unidirectional lay-up and resin damage under 90° unidirectional lay-up.

Spatiotemporal characteristics and socioeconomic factors of PM2.5 heterogeneity in mainland China during the COVID-19 epidemic.

Spatiotemporal variation of PM2.5 in 2018 and 2020 were compared to analyze the impacts of COVID-19, the spatial heterogeneity of PM2.5, and meteorological and socioeconomic impacts of PM2.5 concentrations heterogeneity in China in 2020 were investigated. The results showed that the annual average PM2.5 concentration in 2020 was 32.73 µg/m3 existing a U-shaped variation pattern, which has decreased by 6.38 µg/m3 compared to 2018. A consistent temporal pattern was found in 2018 and 2020 with significant high values in winter and low in summer. PM2.5 declined dramatically in eastern and central China, where are densely populated and economically developed areas during the COVID-19 epidemic compared with previous years, indicating that the significantly decline of social activities had an important effect on the reduction of PM2.5 concentrations. The lowest PM2.5 was found in August because that precipitation had a certain dilution effect on pollutants. January was the most polluted due to centralized coal burning for heating in North China. Overall, the PM2.5 concentrations in China were spatially agglomerated. The highly polluted contiguous zones were mainly located in northwest China and the central plains city group, while the coastal area and Inner Mongolia were areas with good air quality. Negative correlations were found between natural factors (temperature, precipitation, wind speed and relative humidity) and PM2.5 concentrations, with precipitation has the greatest impact on PM2.5, which are beneficial for reducing PM2.5 concentrations. Among the socio-economic factors, proportion of the secondary industry, number of taxis, per capita GDP, population, and industrial nitrogen oxide emissions have positive correlation effects on PM2.5, while the overall social electricity consumption, industrial sulfur dioxide emissions, green coverage in built-up areas, and total gas and liquefied gas supply have negative correlation effects on the PM2.5.

Effects of Seasonal Variation on Spatial and Temporal Distributions of Ozone in Northeast China.

The levels of tropospheric ozone (O3) are closely related to regional meteorological conditions, precursor emissions, and geographical environments, which have a significant negative impact on human health. The concentrations of O3 were relatively low, while the spatial distribution was strongly heterogeneous in Northeast China; however, little is known about how the influencing factors affect the distribution of O3 in Northeast China. Here, the O3 concentration, meteorological observation data, precursors (NO2), and vegetation coverage data from 41 monitoring cities in Northeast China from 2017 to 2020 were collected and analyzed. The spatial-temporal distributions and evolution characteristics of O3 concentrations were investigated using statistical analysis, kriging interpolation, spatial autocorrelation analysis, cold-hot spot analysis, and geographic detectors, and the effects of meteorological factors, NO2, and green land area on O3 concentrations were evaluated seasonally and spatially. The results showed that O3 pollution in Northeast China was generally at a relatively low level and showed a decreasing trend during 2017-2020, with the highest concentrations in the spring and the lowest concentrations in the autumn and winter. May-July had relatively high O3 concentrations, and the over-standard rates were also the highest (>10%). The spatial distribution showed that the O3 concentration was relatively high in the south and low in the northeast across the study area. A globally significant positive correlation was derived from the spatial autocorrelation analysis. The cold-hot spot analysis showed that O3 concentrations exhibited spatial agglomerations of hot spots in the south and cold spots in the north. In Northeast China, the south had hot spots with high O3 pollution, the north had cold spots with excellent O3 levels, and the central region did not exhibit strong spatial agglomerations. A weak significant negative correlation between O3 and NO2 indicated that the emissions of NOx derived from human activities have weak effects on the O3 concentrations, and wind speed and sunshine duration had little effect on spatial differentiation of the O3 concentrations. Spatial variability in O3 concentrations in the spring and autumn was mainly driven by temperature, but in the summer, the influence of temperature was weakened by the relative humidity and precipitation; no factor had strong explanatory power in the winter. The temperature was the only controlling factor in hot spots with high O3 concentrations. In cold spots with low O3 concentrations, the relative humidity and green land area jointly affected the spatial distributions of O3.

Data-model alliance network for the online multi-step thermal warning of energy storage system based on surface temperature diffusion.

As an important type of energy storage, battery energy storage systems have been widely used. However, there are frequent cases of battery explosion due to high temperature. To address this issue, researches have been carried out either in the model-driven or the data-driven aspects to predict the temperature of the battery. In this paper, a two-node electrothermal model and a multi-scale long short-term memory network are established formulating a data-model alliance network (DMAN) for surface temperature diffusion. An improved adaptive boosting algorithm is then employed to enhance the bridge of the two models. Integrating a data-model alliance module (DMAM) and multi-step-ahead thermal warning network (MATWN), this DMAN provides an advanced online multi-step-ahead thermal warning structure to achieve early warning of temperature crossing. Experimental results verify the progressiveness of the proposed technique.

A Versatile Punch Stroke Correction Model for Trial V-Bending of Sheet Metals Based on Data-Driven Method.

During air bending of sheet metals, the correction of punch stroke for springback control is always implemented through repeated trial bending until achieving the forming accuracy of bending parts. In this study, a modelling method for correction of punch stroke is presented for guiding trial bending based on a data-driven technique. Firstly, the big data for the model are mainly generated from a large number of finite element simulations, considering many variables, e.g., material parameters, dimensions of V-dies and blanks, and processing parameters. Based on the big data, two punch stroke correction models are developed via neural network and dimensional analysis, respectively. The analytic comparison shows that the neural network model is more suitable for guiding trial bending of sheet metals than the dimensional analysis model, which has mechanical significance. The actual trial bending tests prove that the neural-network-based punch stroke correction model presents great versatility and accuracy in the guidance of trial bending, leading to a reduction in the number of trial bends and an improvement in the production efficiency of air bending.

Microstructure and Mechanical Properties of Al-Mg-Si Similar Alloy Laminates Produced by Accumulative Roll Bonding.

As the applications of heterogeneous materials expand, aluminum laminates of similar materials have attracted much attention due to their greater bonding strength and easier recycling. In this work, an alloy design strategy was developed based on accumulative roll bonding (ARB) to produce laminates from similar materials. Twin roll casting (TRC) sheets of the same composition but different cooling rates were used as the starting materials, and they were roll bonded up to three cycles at varying temperatures. EBSD showed that the two TRC sheets deformed in distinct ways during ARB processes at 300 °C. Major recrystallizations were significant after the first cycle on the thin sheet and after the third cycle on the thick sheet. The sheets were subject to subsequent aging for better mechanical properties. TEM observations showed that the size and distribution of nano-precipitations were different between the two sheet sides. These nano-precipitations were found to significantly promote precipitation strengthening, and such a promotive effect was referred to as hetero-deformation induced (HDI) strengthening. Our work provides a new promising method to prepare laminated heterogeneous materials with similar alloy TRC sheets.

Multi-step ahead thermal warning network for energy storage system based on the core temperature detection.

The energy storage system is an important part of the energy system. Lithium-ion batteries have been widely used in energy storage systems because of their high energy density and long life. However, the temperature is still the key factor hindering the further development of lithium-ion battery energy storage systems. Both low temperature and high temperature will reduce the life and safety of lithium-ion batteries. In actual operation, the core temperature and the surface temperature of the lithium-ion battery energy storage system may have a large temperature difference. However, only the surface temperature of the lithium-ion battery energy storage system can be easily measured. The estimation method of the core temperature, which can better reflect the operation condition of the lithium-ion battery energy storage system, has not been commercialized. To secure the thermal safety of the energy storage system, a multi-step ahead thermal warning network for the energy storage system based on the core temperature detection is developed in this paper. The thermal warning network utilizes the measurement difference and an integrated long and short-term memory network to process the input time series. This thermal early warning network takes the core temperature of the energy storage system as the judgment criterion of early warning and can provide a warning signal in multi-step in advance. This detection network can use real-time measurement to predict whether the core temperature of the lithium-ion battery energy storage system will reach a critical value in the following time window. And the output of the established warning network model directly determines whether or not an early emergency signal should be sent out. In the end, the accuracy and effectiveness of the model are verified by numerous testing.

Supplemental Plant Extracts From Flos lonicerae in Combination With Baikal skullcap Attenuate Intestinal Disruption and Modulate Gut Microbiota in Laying Hens Challenged by Salmonella pullorum.

Dietary inclusions of baicalin and chlorogenic acid were beneficial for intestinal health in pigs. Nevertheless, it is unknown whether these plant-derived products had protection for intestine against bacterial challenge in chickens. This study was aimed at evaluating the potential mitigating effects of plant extracts (PE) from Flos lonicerae combined with Baikal skullcap (the active components are chlorogenic acid and baicalin) on intestinal disruption and dysbacteriosis induced by Salmonella pullorum in laying hens. A total of 216 41-week-old layers were randomly divided into 3 groups (6 replicates per group): negative control (NC), S. pullorum-infected positive control (PC), and the S. pullorum-infected group with supplementation of PE at 1000 mg/kg. All birds except those in NC were challenged with S. pullorum at the end of 4 weeks of the experiment. S. pullorum challenge impaired (P < 0.05) the production performance (egg production, feed intake, and feed efficiency) of laying hens, increased (P < 0.05) serum endotoxin content and frequency of Salmonella-positive organs, as well as up-regulated (P < 0.05) ileal expression of pro-inflammatory cytokines including IFNG, TNFA, IL8, and IL1B, whereas PE addition reversed (P < 0.05) these changes and increased (P < 0.05) ileal IL10 expression. Supplemental PE moderated ileal microbiota dysbiosis in challenged birds, characterized by a reduced abundance of Firmicutes along with increased abundances of Bacteroidetes (Bacteroides), Deferribacteres and several butyrate-producers such as Prevotellaceae, Faecalibacterium, Blautia, Butyricicoccus, Lachnoclostridium, and Olsenella, which may assist with energy harvesting and boost anti-inflammatory capacity of host. The decreased abundance of Firmicutes with the increased abundance of Bacteroidetes caused by PE addition had positive correlations with the decreased expression of ileal pro-inflammatory cytokines. The increased abundances of Bacteroidetes (Bacteroides) and Prevotellaceae following PE addition were also positively correlated with the improvement of performance (egg production and feed intake) of laying hens. Collectively, supplemental PE from Flos lonicerae in combination with Baikal skullcap alleviated S. pullorum-induced intestinal disruption and performance impairment in laying hens, which could be at least partially responsible by the modulation of gut microbial composition.

Ammonium transformed into nitrous oxide via nitric oxide by Pseudomonas putida Y-9 under aerobic conditions without hydroxylamine as intermediate.

Previous studies have reported that hydroxylamine (NH2OH) is an inevitable intermediate of the ammonium (NH4+) oxidation pathway under aerobic conditions. In this study, Pseudomonas putida Y-9 was found to oxidize ammonium into N2O via NO without the accumulation of NH2OH and NO2- under aerobic conditions. NH2OH was nearly completely transformed into NO2- whether NH4+ was present in the medium, and NH4+ could accelerate the transformation of NH2OH to NO2- by promoting Y-9 growth. NH4+ was oxidized rapidly by Y-9 with or without the presence of NH2OH in the medium, and the decrease of total nitrogen reached 30.65 mg/L and 39.38 mg/L, respectively, which indicates that NH2OH inhibits the transformation efficiency of NH4+ to N2O. Gene amplification and enzyme assays demonstrated that ammonia monooxygenase doesn't exist in Y-9. All results show that NH4+ can be transformed into N2O via NO by Y-9 under aerobic conditions without NH2OH as intermediate.

A Hierarchical Copper Oxide-Germanium Hybrid Film for High Areal Capacity Lithium Ion Batteries.

Self-supported electrodes represent a novel architecture for better performing lithium ion batteries. However, lower areal capacity restricts their commercial application. Here, we explore a facial strategy to increase the areal capacity without sacrificing the lithium storage performance. A hierarchical CuO-Ge hybrid film electrode will not only provide high areal capacity but also outstanding lithium storage performance for lithium ion battery anode. Benefiting from the favorable structural advance as well as the synergic effect of the Ge film and CuO NWs array, the hybrid electrode exhibits a high areal capacity up to 3.81 mA h cm-2, good cycling stability (a capacity retention of 90.5% after 150 cycles), and superior rate performance (77.4% capacity remains even when the current density increased to 10 times higher).