Search for: All records

An instantaneous and precise coating inspection method is imperative to mitigate the risk of flaws, defects, and discrepancies on coated surfaces. While many studies have demonstrated the effectiveness of automated visual inspection (AVI) approaches enhanced by computer vision and deep learning, critical challenges exist for practical applications in the manufacturing domain. Computer vision has proven to be inflexible, demanding sophisticated algorithms for diverse feature extraction. In deep learning, supervised approaches are constrained by the need for annotated datasets, whereas unsupervised methods often result in lower performance. Addressing these challenges, this paper proposes a novel deep learning-based automated visual inspection (AVI) framework designed to minimize the necessity for extensive feature engineering, programming, and manual data annotation in classifying fuel injection nozzles and discerning their coating interfaces from scratch. This proposed framework comprises six integral components: It begins by distinguishing between coated and uncoated nozzles through gray level co-occurrence matrix (GLCM)-based texture analysis and autoencoder (AE)-based classification. This is followed by cropping surface images from uncoated nozzles, and then building an AE model to estimate the coating interface locations on coated nozzles. The next step involves generating autonomously annotated datasets derived from these estimated coating interface locations. Subsequently, a convolutional neural network (CNN)-based detection model is trained to accurately localize the coating interface locations. The final component focuses on enhancing model performance and trustworthiness. This framework demonstrated over 95% accuracy in pinpointing the coating interfaces within the error range of ± 6 pixels and processed at a rate of 7.18 images per second. Additionally, explainable artificial intelligence (XAI) techniques such as t-distributed stochastic neighbor embedding (t-SNE) and the integrated gradient substantiated the reliability of the models.

 

This study introduces a non-invasive approach to monitor operation and productivity of a legacy pipe bending machine in real-time based on a lightweight convolutional neural network (CNN) model and internal sound as input data. Various sensors were deployed to determine the optimal sensor type and placement, and labels for training and testing the CNN model were generated through the meticulous collection of sound data in conjunction with webcam videos. The CNN model, which was optimized through hyperparameter tuning via grid search and utilized feature extraction using Log-Mel spectrogram, demonstrated notable prediction accuracies in the test. However, when applied in a real-world manufacturing scenario, the model encountered a significant number of errors in predicting productivity. To navigate through this challenge and enhance the predictive accuracy of the system, a buffer algorithm using the inferences of CNN models was proposed. This algorithm employs a queuing method for continuous sound monitoring securing robust predictions, refines the interpretation of the CNN model inferences, and enhances prediction outcomes in actual implementation where accuracy of monitoring productivity information is crucial. The proposed lightweight CNN model alongside the buffer algorithm was successfully deployed on an edge computer, enabling real-time remote monitoring.

 

Coastal upwelling, driven by alongshore winds and characterized by cold sea surface temperatures and high upper-ocean nutrient content, is an important physical process sustaining some of the oceans’ most productive ecosystems. To fully understand the ocean properties in eastern boundary upwelling systems, it is important to consider the depth of the source waters being upwelled, as it affects both the SST and the transport of nutrients toward the surface. Here, we construct an upwelling source depth distribution for parcels at the surface in the upwelling zone. We do so using passive tracers forced at the domain boundary for every model depth level to quantify their contributions to the upwelled waters. We test the dependence of this distribution on the strength of the wind stress and stratification using high-resolution regional ocean simulations of an idealized coastal upwelling system. We also present an efficient method for estimating the mean upwelling source depth. Furthermore, we show that the standard deviation of the upwelling source depth distribution increases with increasing wind stress and decreases with increasing stratification. These results can be applied to better understand and predict how coastal upwelling sites and their surface properties have and will change in past and future climates.

 

Autophagy in eukaryotes functions to maintain homeostasis by degradation and recycling of long-lived and unwanted cellular materials. Autophagy plays important roles in pathogenicity of various fungal pathogens, suggesting that autophagy is a novel target for development of antifungal compounds. Here, we describe bioluminescence resonance energy transfer (BRET)-based high-throughput screening (HTS) strategy to identify compounds that inhibit fungal ATG4 cysteine protease-mediated cleavage of ATG8 that is critical for autophagosome formation. We identified ebselen (EB) and its analogs ebselen oxide (EO) and 2-(4-methylphenyl)−1,2-benzisothiazol-3(2H)-one (PT) as inhibitors of fungal pathogensBotrytis cinereaandMagnaporthe oryzaeATG4-mediated ATG8 processing. The EB and its analogs inhibit spore germination, hyphal development, and appressorium formation inAscomycotapathogens,B. cinerea, M. oryzae,Sclerotinia sclerotiorumandMonilinia fructicola. Treatment with EB and its analogs significantly reduced fungal pathogenicity. Our findings provide molecular insights to develop the next generation of antifungal compounds by targeting autophagy in important fungal pathogens.

 

We consider an approach based on property rights mismatch to analyze conflict over radio spectrum. A mismatch occurs when the bundle of property rights created to enable social coordination fails to achieve this objective, leading to missed opportunities for productive exchange. With radio spectrum, these conflicts often result from technological changes that increase prospects (and satisfy demand for) sharing spectrum. Our focus is on how property regimes contribute to conflict as a result of mismatch, as well as how they might be resolved, for two examples of spectrum: passive and active spectrum uses and mobile services on the unlicensed band. 

The bright starλSer hosts a hot Neptune with a minimum mass of 13.6M_⊕and a 15.5 day orbit. It also appears to be a solar analog, with a mean rotation period of 25.8 days and surface differential rotation very similar to the Sun. We aim to characterize the fundamental properties of this system and constrain the evolutionary pathway that led to its present configuration. We detect solar-like oscillations in time series photometry from the Transiting Exoplanet Survey Satellite, and we derive precise asteroseismic properties from detailed modeling. We obtain new spectropolarimetric data, and we use them to reconstruct the large-scale magnetic field morphology. We reanalyze the complete time series of chromospheric activity measurements from the Mount Wilson Observatory, and we present new X-ray and ultraviolet observations from the Chandra and Hubble space telescopes. Finally, we use the updated observational constraints to assess the rotational history of the star and estimate the wind braking torque. We conclude that the remaining uncertainty on the stellar age currently prevents an unambiguous interpretation of the properties ofλSer, and that the rate of angular momentum loss appears to be higher than for other stars with a similar Rossby number. Future asteroseismic observations may help to improve the precision of the stellar age.