Search

Name Entity Recognition (NER) aims to recognize entities in the engine room domain from unstructured engine room domain text. But in the engine room domain, the entities are diverse and complex, and there is a nesting phenomenon, resulting in a low entity recognition rate. In this paper, a deep learning method incorporating language models is proposed to enhance the entity recognition performance within the engine room. domain. Firstly, the Bidirectional Encoder Representation from Transformers (BERT) language model is employed to train text feature extraction, acquiring a matrix of vector representations at the word level. Secondly, the trained word vectors are fed into the Bidirectional Gated Recurrent Unit (BiGRU) for contextual semantic entity feature extraction. Finally, the global optimal sequence is extracted by combining with the Conditional Random Field (CRF) model to obtain the named entities in the ship cabin semantics. The experimental results show that the proposed algorithm can obtain better F1 values for all three types of entity recognition. Compared with BERT-BiGRU, the overall accuracy of entity identification, recall rate and F1 value are improved by 1.35%, 1.45% and 1.40%, respectively.

By utilizing top-of-atmosphere radiation (TOAR) data from China’s new generation of geostationary satellites (FY-4A and FY-4B) along with interpretable machine learning models, near-surface particulate matter concentrations in China were estimated, achieving hourly temporal resolution, 4 km spatial resolution, and 100% spatial coverage. First, the cloudless TOAR data were matched and modeled with the solar radiation products from the ERA5 dataset to construct and estimate a fully covered TOAR dataset under assumed clear-sky conditions, which increased coverage from 20–30% to 100%. Subsequently, this dataset was applied to estimate particulate matter. The analysis demonstrated that the fully covered TOAR dataset (R2 = 0.83) performed better than the original cloudless dataset (R2 = 0.76). Additionally, using feature importance scores and SHAP values, the impact of meteorological factors and air mass trajectories on the increase in PM10 and PM2.5 during dust events were investigated. The analysis of haze events indicated that the main meteorological factors driving changes in particulate matter included air pressure, temperature, and boundary layer height. The particulate matter concentration products obtained using fully covered TOAR data exhibit high coverage and high spatiotemporal resolution. Combined with data-driven interpretable machine learning, they can effectively reveal the influencing factors of particulate matter in China.

Abstract In recent years, advancements in industries such as aerospace, military weaponry, automobiles, locomotives, and shipbuilding have led to a surge in the demand for bent and rolled components, along with increasingly stringent requirements for rolling precision. However, the traditional hydraulic cylinder feeding solution has hindered further enhancements in the accuracy of rolled profile contours. Additionally, owing to variations in profile specifications, material properties, and an assortment of random factors during the forming process, the applicability of existing forming formulas remains limited, rendering them suitable only for profile processing under specific circumstances. To address these challenges, servo electric cylinders have been introduced as a replacement for traditional hydraulic cylinders, and the mechanical structure of a four-roll bending machine has been re-engineered. This innovation has demonstrated the feasibility of employing servo electric cylinders in four-roll CNC bending machines for profile bending, resulting in higher control precision and faster response times, ultimately providing a comprehensive design solution for four-roll CNC bending machines. In response to the limited universality of existing forming formulas, the actual R (profile forming curvature) and d (servo electric cylinder feed) values from the four-roll CNC bending machine have been utilized, and curve fitting methods have been implemented as the foundation for the automatic control model. This approach offers a high degree of universality, making it suitable for a wide range of applications. Moreover, as the number of trials increased, forming precision progressively improved.

Precise cloud and aerosol identification hold paramount importance for a thorough comprehension of atmospheric processes, enhancement of meteorological forecasts, and mitigation of climate change. This study devised an automatic denoising cloud–aerosol classification deep learning algorithm, successfully achieving cloud–aerosol identification in atmospheric vertical profiles utilizing CALIPSO L1 data. The algorithm primarily consists of two components: denoising and classification. The denoising task integrates an automatic denoising module that comprehensively assesses various methods, such as Gaussian filtering and bilateral filtering, automatically selecting the optimal denoising approach. The results indicated that bilateral filtering is more suitable for CALIPSO L1 data, yielding SNR, RMSE, and SSIM values of 4.229, 0.031, and 0.995, respectively. The classification task involves constructing the U-Net model, incorporating self-attention mechanisms, residual connections, and pyramid-pooling modules to enhance the model’s expressiveness and applicability. In comparison with various machine learning models, the U-Net model exhibited the best performance, with an accuracy of 0.95. Moreover, it demonstrated outstanding generalization capabilities, evaluated using the harmonic mean F1 value, which accounts for both precision and recall. It achieved F1 values of 0.90 and 0.97 for cloud and aerosol samples from the lidar profiles during the spring of 2019. The study endeavored to predict low-quality data in CALIPSO VFM using the U-Net model, revealing significant differences with a consistency of 0.23 for clouds and 0.28 for aerosols. Utilizing U-Net confidence and a 532 nm attenuated backscatter coefficient to validate medium- and low-quality predictions in two cases from 8 February 2019, the U-Net model was found to align more closely with the CALIPSO observational data and exhibited high confidence. Statistical comparisons of the predicted geographical distribution revealed specific patterns and regional characteristics in the distribution of clouds and aerosols, showcasing the U-Net model’s proficiency in identifying aerosols within cloud layers.

With the rapid development of profile processing industry, the processing shape, efficiency, and consistency of profiles are more and more demanding. In this case, the progress of bending machine tools was very important. In this study, the disadvantages and shortcomings of traditional three-roll bending machine are investigated, and a new design of three-roll bending machine is proposed, including a new mechanical structure, hydraulic pressure, and control system. ABAQUS was used to analyze the constrained mode of the table, and the first six order natural frequencies and natural vibration modes were obtained. A mathematical model was established to analyze the relationship between the pressure displacement and the forming radius under ideal working conditions, and the limit position of the downward movement of the lower press roll and the speed relationship between the lower press roll and the support roll are discussed. Based on the experimental data, the nonlinear curve fitting was carried out on the rebound compensation algorithm of asymmetric rolling bending forming. The fitting rebound compensation algorithm was carried out on the symmetric rolling bending forming experiment. The experimental results show that this algorithm can be applied to both symmetric rolling bending and asymmetric rolling bending.

Sulfur dioxide (SO2) is one of the main pollutants in China’s atmosphere, but the spatial distribution of ground-based SO2 monitors is too sparse to provide a complete coverage. Therefore, obtaining a high spatial resolution of SO2 concentration is of great significance for SO2 pollution control. In this study, based on the LightGBM machine learning model, combined with the top-of-atmosphere radiation (TOAR) of Himawari-8 and additional data such as meteorological factors and geographic information, a high temporal and spatial resolution TOAR-SO2 estimation model in eastern China (97–136°E, 15–54°N) is established. TOAR and meteorological factors are the two variables that contribute the most to the model, and both of their feature importance values exceed 30%. The TOAR-SO2 model has great performance in estimating ground-level SO2 concentrations with 10-fold cross validation R2 (RMSE) of 0.70 (16.26 μg/m3), 0.75 (12.51 μg/m3), 0.96 (2.75 μg/m3), 0.97 (2.16 μg/m3), and 0.97 (1.71 μg/m3) when estimating hourly, daily, monthly, seasonal, and annual average SO2. Taking North China as main study area, the annual average SO2 is estimated. The concentration of SO2 in North China showed a downward trend since 2016 and decreased to 15.19 μg/m3 in 2020. The good agreement between ground measured and model estimated SO2 concentrations highlights the capability and advantage of using the model to monitor spatiotemporal variations of SO2 in Eastern China.

With the advancement of urbanization in China, effective control of pollutant emissions and air quality have become important goals in current environmental management. Nitrogen dioxide (NO2), as a precursor of tropospheric ozone and fine particulate matter, plays a significant role in atmospheric chemistry research and air pollution control. However, the uneven ground monitoring stations and low temporal resolution of polar-orbiting satellites set challenges for accurately assessing near-surface NO2 concentrations. To address this issue, a spatiotemporal refined NO2 retrieval model was established for China using the geostationary satellite Himawari-8. The spatiotemporal characteristics of NO2 were analyzed and its contribution factors were explored. Firstly, seven Himawari-8 channels sensitive to NO2 were selected by using the forward feature selection based on information entropy. Subsequently, a 2DCNN-LSTM network model was constructed, incorporating the selected channels and meteorological variables as retrieval factors to estimate hourly NO2 in China from March 2018 to February 2020 (with a resolution of 0.05°, per hour). The performance evaluation demonstrates that the full-channel 2DCNN-LSTM model has good fitting capability and robustness (R2 = 0.74, RMSE = 10.93), and further improvements were achieved after channel selection (R2 = 0.87, RMSE = 6.84). The 10-fold cross-validation results indicate that the R2 between retrieval and measured values was above 0.85, the MAE was within 5.60, and the RMSE iwas within 7.90. R2 varied between 0.85 and 0.90, showing better validation at mid-day (R2 = 0.89) and in spring and fall transition seasons (R2 = 0.88 and R2 = 0.90). To investigate the cooperative effect of meteorological factors and other air pollutants on NO2, statistical methods (beta coefficients) were used to test the factor interpretability. Meteorological factors as well as other pollutants were analyzed. From a statistical perspective, PM2.5, boundary layer height, and O3 were found to have the largest impacts on near-surface NO2 concentrations, with each standard deviation change in these factors leading to 0.28, 0.24, and 0.23 in standard deviations of near-surface NO2, respectively. The findings of this study contribute to a comprehensive understanding of the spatiotemporal distribution of NO2 and provide a scientific basis for formulating targeted air pollution policies.

Blind signatures have been widely applied when privacy preserving is required, and the delegation of blind signature rights and a proxy blind signature (Proxy-BS) become necessary when the signer cannot sign. Existing Proxy-BS schemes are based on traditional cryptographically hard problems, and they cannot resist quantum attacks. Moreover, most current Proxy-BS schemes depend on public key infrastructure (PKI), which leads to high certificate storage and management overhead. To simplify key management and resist quantum attacks, we propose a post-quantum secure identity-based proxy blind signature (ID-Proxy-BS) scheme on a lattice using a matrix cascade technique and lattice cryptosystem. Under the random oracle model (ROM), the security of the proposed scheme is proved. Security shows that the proposed scheme assures security against quantum attacks and satisfies the correctness, blindness, and unforgeability. In addition, we apply the ID-Proxy-BS scheme on a lattice to e-voting and propose a quantum-resistant proxy e-voting system, which is resistant to quantum attacks and achieves the efficiency of e-voting.

The COVID-19 pandemic poses a serious global threat to human health. In China, the government immediately implemented lockdown measures to curb the spread of this virus. These measures severely affected transportation and industrial production across the country, resulting in a significant change in the concentration of air pollutants. In this study, the Euclidean distance method was used to select the most similar meteorological field during the COVID-19 lockdown period. Changes in the concentration of air pollutants in China were analyzed under similar meteorological background conditions. Results indicate that, compared with data from 2015–2019, air quality in China significantly improved; with the exception of ozone (O3), the concentration of major air pollutants declined. Compared with baseline conditions, the reduction of air pollutants in China from 25 January to 22 February 2020 (Period 2) was the most significant. In particular, NO2 decreased by 41.7% in the Yangtze River Delta. In Period 2, the reduction of air pollutants in areas other than Hubei gradually decreased, but the reduction of NO2 in Wuhan reached 61.92%, and the reduction of air pollutants in various regions after February 23 was significantly reduced. By excluding the influence of meteorological factors and calculating the contribution of human activities to atmospheric pollutants by linear fitting, in Period 2 the effect of artificial controls on NO2 in Wuhan attained 30.66%, and reached 48.17% from 23 February to 23 March (Period 3). Results from this investigation provides effective theoretical support for pollution prevention and control in China.

Phase change memory (PCM) has been regarded as one of the most promising candidates for the next-generation nonvolatile memory. In this paper, we propose PtSb _2 Te (PST) phase change material for phase change memory. The doping of Pt improves the crystallization temperature and Ten-year data-retention temperature of Sb _2 Te to 180 °C, 192 °C, 204 °C and 117 °C,123 °C,137 °C, and refines the grain to about 10 nm. At the same time, the density change of Sb _2 Te film after phase transition is reduced to 4.19% due to the addition of Pt. There are no other new phases formed in PST film except hexagonal Sb _2 Te phase. For PST-based phase change memory cell, only 10 ns electrical pulse is required to complete the reversible operation with a Reset voltage lower than 4.3 V. At the same time, the number of cycle operations of the memory cell exceeds 10 ^5 and it has a lower resistance drift coefficient as 0.019.

At present, the network data under the environment of industrial information physical system is larger and more complex. Traditionally, feature extraction by machine learning is cumbersome and computation-intensive, which is not conducive to anomaly detection of industrial network data. To solve the above problems, this paper proposes a stacked denoised auto-encoding network based on kernel principal component analysis for industrial cyber physical systems intrusion detection. Firstly, a novel kernel principal component analysis method is used to reduce the data feature dimension and obtain a new low-dimension feature data set. Then, a multi-stacked denoised auto-encoding network model is used to classify and identify the data after dimensionality reduction by voting. Experimental results show that the proposed method has better classification performance and detection efficiency by comparing the state-of-the-art intrusion detection methods. [ABSTRACT FROM AUTHOR]

The asymmetric structure expands the voltage window of supercapacitors in aqueous electrolyte solutions, thereby significantly increasing energy density. However, exploring high-performance negative electrode materials is of utmost importance, on the premise that positive electrode materials have been extensively developed. This study explores the homogeneous composition of iron oxide and graphene via in situ laser induction on the precursor film of polyimide foam containing Fe3+ ions. 3D interconnected graphene was prepared under laser direct writing, while Fe3+ ions were thermally reduced to obtain iron oxide (Fe3+/Fe2+). By adjusting the concentration of Fe3+ ions in the precursor polyimide foam and laser parameter settings, the Fe3+/Fe2+ ratio was regulated to exhibit optimal electrochemical performance. When employed as a negative electrode material for assessing the electrochemical performance, it displayed a notable area capacitance of 654.3 mF cm2 at a current density of 1 mA cm2. In the assembled aqueous asymmetric supercapacitors, the specific energy density was 33.25 mW h cm2 at a power density of 750 mW cm2 and retained 86.8% of its capacitance even after 10 000 charge-discharge cycles. This method offers a new approach for synthesizing laserinduced multivalent compounds and serves as a reference for efficiently producing negative electrodes of an asymmetric supercapacitor. [ABSTRACT FROM AUTHOR]