Search

The accurate prediction of airplane engine failure can provide a reasonable decision basis for airplane engine maintenance, effectively reducing maintenance costs and reducing the incidence of failure. According to the characteristics of the monitoring data of airplane engine sensors, this work proposed a remaining useful life (RUL) prediction model based on principal component analysis and bidirectional long short-term memory. Principal component analysis is used for feature extraction to remove useless information and noise. After this, bidirectional long short-term memory is used to learn the relationship between the state monitoring data and remaining useful life. This work includes data preprocessing, the construction of a hybrid model, the use of the NASA’s Commercial Aerodynamic System Simulation (C-MAPSS) data set for training and testing, and the comparison of results with those of support vector regression, long short-term memory and bidirectional long short-term memory models. The hybrid model shows better prediction accuracy and performance, which can provide a basis for formulating a reasonable airplane engine health management plan.

Influence of color fixation agent (CFA) and dyebath pH in secondary alcohol ethoxylate (SAE)-based reverse micellar dyeing system of cotton with reactive dyes was investigated and compared with water-based dyeing system using different alkali (i.e. CFA) such as: (i) sodium bicarbonate (NaHCO3), (ii) sodium carbonate (Na2CO3) and (iii) sodium hydroxide (NaOH). The color, tensile strength, fastness and surface morphological properties of dyed samples were examined. Experimental results showed that samples dyed with Na2CO3 can achieve the highest color yield, followed by NaHCO3 and NaOH in both water-based and reverse micellar dyeing system. The color yield and reflectance percentage of the dyed cotton samples were found to be closely related to the dyebath pH value. Relative unlevelness indices (RUI) also reflected that cotton samples dyed with NaOH in reverse micellar dyeing system have a higher chance of color unlevelness when compared with NaHCO3 and Na2CO3. Tensile strength results affirm that higher alkalinity of dyebath could cause higher strength loss to the colored cotton samples. Both cotton samples dyed by water and SAE approach showed good to excellent color fastness properties while scanning electron microscopic (SEM) images exhibit that the use of different alkalis may cause some damage to the cotton fiber.

Abstract Printed circuit board (PCB) may display diverse surface defects in manufacturing. These defects not only influence aesthetics but can also affect the performance of the PCB and potentially damage the entire board. Thus, achieving efficient and highly accurate detection of PCB surface defects is fundamental for quality control in fabrication. The rapidly advancing deep learning (DL) technology holds promising prospects for providing accurate and efficient detection methods for surface defects on PCB. To facilitate DL model training, it is imperative to compile a comprehensive dataset encompassing diverse surface defect types found on PCB at a significant scale. This work categorized PCB surface defects into 9 distinct categories based on factors such as their causes, locations, and morphologies and developed a dataset of PCB surface defect (DsPCBSD+). In DsPCBSD+, a total of 20,276 defects were annotated manually by bounding boxes on the 10,259 images. This openly accessible dataset is aimed accelerating and promoting further researches and advancements in the field of DL-based detection of PCB surface defect.

Coalbed methane well sand (pulverized coal) problem restricts the production life of coalbed methane well, resulting in high maintenance costs, reduce productivity, and because of the large contact area between thin interbed coal seam and surrounding rock, the problem of sand production (pulverized coal) is prominent. In the Surat Basin of Australia, the coal seam cementation is loose and the coal/mud/sandstone interlayer is complex. In the statistical wells, 100% of the production wells have different degrees of sand production problems, and 33.5% of which have serious sand production, frequent workover operations, and high production costs. Based on the systematic analysis of the reservoir characteristics, sand production characteristics and production rules in Surat Basin, the comprehensive sand discharge prevention technology of “expansion packer + blind tube” and “screw pump + slurry rotor + automatic shunt valve + drilling through casing shoes” is adopted according to the research on the particle settlement law, combined with the prediction of sand production level and the optimization of sand control technology. The problem of sand production in coal measure strata in Surat Basin has been solved in stages. The field application results show that the average continuous production time of a single well increases from 275 days to nearly 400 days, and the workover frequency is reduced by nearly 50%.

Abstract To achieve the intelligent perception of traffic video and overcome the dispersion of computing modules and the separation processing of multiple tasks, efficient chained centre network (ECCNet) is proposed as a unified framework, accomplishing detection, vehicle classification, tracking, and vehicle speed estimation simultaneously. First, for the speed‐accuracy trade‐off, CA‐CenterNet is presented, which can detect vehicles and classify vehicle types to serve cross‐frame tasks more accurately by embedding coordinate attention. Second, 3D convolution is employed to construct a self‐adaptive branch for data association and speed estimation, respectively. This self‐adaptive approach leverages the power of deep learning to enhance tracking performance and avoid camera calibration via capturing motion information across frames. Moreover, a chained structure is adopted to reuse the backbone feature map. The spatio‐temporal information of adjacent frames can be extracted at almost no additional cost. Finally, the above single‐frame and cross‐frame tasks are integrated into a unified multi‐task collaborative optimization model. The effectiveness of ECCNet is verified with experiments on the UA‐DETRAC dataset. ECCNet achieves 55.5% MOTA, 0.76 F1 value, and 3.10 MAE with an inference speed of 32.5 Hz in the tracking, classification, and speed estimation tasks, respectively.

Remaining useful life prediction of a milling tool is one of the determinants in making scientific maintenance decision for the CNC machine tool. Predicting the RUL accurately can improve machining efficiency and the quality of product. Deep learning methods have strong learning capability in RUL prediction and are extensively used. Multiscale CNN, a typical deep learning model in RUL prediction, has a large number of parameters because of its parallel convolutional pathways, resulting in high computing cost. Besides, the MSCNN ignores various influences of different scales of degradation features on RUL prediction accuracy. To address the issue, a pyramid CNN (PCNN) is proposed for RUL prediction of the milling tool in this paper. Group convolution is used to replace parallel convolutional pathways to extract multiscale features without additional large number of parameters. And the channel attention with soft assignment is used to select the key degradation features, considering different sensors and scales. The milling tool wear experiments show that the score value of the proposed method achieved 51.248 ± 1.712 and the RMSE achieved 19.051 ± 0.804, confirming better performance of the proposed method compared with the traditional MSCNN and other deep learning methods. Besides, the number of parameters of the proposed method is reduced by 62.6% and 54.8% compared with the MSCNN with self-attention and the MSCNN methods, confirming its lower computing cost.

Electrospun nanofibers have been widely used in dentistry due to their excellent properties, such as high surface area and high porosity, this bibliometric study aimed to review the application fields, research status, and development trends of electrospun nanofibers in different fields of dentistry in recent years. All of the data were obtained from the Web of Science from 2004 to 2021. Origin, Microsoft Excel, VOSviewer, and Carrot2 were used to process, analyze, and evaluate the publication year, countries/region, affiliations, authors, citations, keywords, and journal data. After being refined by the year of publication, document types and research fields, a total of 378 publications were included in this study, and an increasing number of publications was evident. Through linear regression calculations, it is predicted that the number of published articles in 2022 will be 66. The most published journal about electrospun dental materials is Materials Science & Engineering C-Materials for Biological Applications, among the six core journals identified, the percent of journals with Journal Citation Reports (JCR) Q1 was 60%. A total of 17.60% of the publications originated from China, and the most productive institution was the University of Sheffield. Among all the 1949 authors, the most productive author was Marco C. Bottino. Most electrospun dental nanofibers are used in periodontal regeneration, and Polycaprolactone (PCL) is the most frequently used material in all studies. With the global upsurge in research on electrospun dental materials, bone regeneration, tissue regeneration, and cell differentiation and proliferation will still be the research hotspots of electrospun dental materials in recent years. Extensive collaboration and citations among authors, institutions and countries will also reach a new level.

Drude's equation, a classical equation, can be used to express the properties of optic polarization. In the paper, an optimized two-term Drude's equation is introduced for expressing the specific rotation. The optical rotation angle for each wavelength is measured by a charge-coupled device. In order to verify the precision and versatility of the equation, we compare the obtained specific rotation with published analysis at a wavelength of 589.3 nm. Moreover, the two-term Drude's equation is translated into calculate the approximatively individual concentration of the molecules in aqueous solution. The calculation is based on the linear functional relation and fitting parameters of total rotation without knowing the ranges of concentrations and setting constraints. The viability and flexibility of this method demonstrate the potential applications in optics.

Structural-coloured poly(styrene-methyl methacrylate-acrylic acid) (Poly(St-MMA-AA)) deposited carbon fabrics (Poly(St-MMA-AA)/PCFs) with fascinating colours (salmon, chartreuse, springgreen, skyblue, mediumpurple) changing with the (Poly(St-MMA-AA) nanoparticle sizes can be facilely fabricated by the thermal-assisted gravity sedimentation method that facilitates the self-assembly of Poly(St-MMA-AA) colloidal nanoparticles to generate photonic crystals. The particle sizes of Poly(St-MMA-AA) copolymer with core/shell structure varying from 308.3 nm to 213.1 nm were controlled by adjusting the amount of emulsifier during emulsion polymerisation. The presence of the intrinsic chemical information of Poly(St-MMA-AA) copolymer has been ascertained by Raman and Fourier Transform Infrared (FT-IR) Spectroscopy analysis. Colour variation of the as-prepared structural-coloured carbon fabrics (Poly(St-MMA-AA)/PCFs) before and after dipping treatment were captured while using an optical microscope. The structural colours of Poly(St-MMA-AA)/PCFs were assessed by calculating the diffraction bandgap according to Bragg’s and Snell’s laws. The Poly(St-MMA-AA) photonic crystal films altered the electrical properties of carbon fabrics with the resistivity growing by five orders of magnitude. The differential electrical resistivity between Poly(St-MMA-AA)/PCFs and wet Poly(St-MMA-AA)/PCFs combined with the corresponding tunable colours can be potentially applied in several promising areas, such as smart displays, especially signal warning displays for traffic safety.

In this study, we simulated the electric field distribution of side-by-side electrospinning by using the finite element method (FEM), and studied the effects of spinneret wall thickness, spinning voltage and receiving distance on the distribution of the electrostatic field. The receiving distance was selected as a variable in the experimental, a series of PAN/PSA composite nanofiber membranes were prepared by using a self-made side by side electrospinning device. The membranes were tested by Fourier-transform infrared (FTIR), thermogravimetric analysis (TG), and scanning electron microscope (SEM). The prepared membranes were also treated by high-temperature treatment, and the change of fiber diameter and conductivity of the membrane before and after high-temperature treatment were studied. It was found that the PAN/PSA carbonized nanofibers could achieve a better performance in heat resistance and conductivity at 200 mm receiving distance.