Search

Seamless positioning and navigation requires an integration of outdoor and indoor positioning systems. Until recently, these systems mostly function in-silos. Though GNSS has become a standalone system for outdoors, no unified positioning modality could be found for indoor environments. Wi-Fi and Bluetooth signals are popular choices though. Increased adoption of different machine learning techniques for indoor–outdoor context detection and localization could be witnessed in the recent literature. The difficulty in precise data annotation, need for sensor fusion, the effect of different hardware configurations pose critical challenges that affect the success of indoor–outdoor (IO) positioning systems. Wireless sensor-based techniques are explicitly programmed, hence estimating locations dynamically becomes challenging. Machine learning and deep learning techniques can be used to overcome such situations and react appropriately by self-learning through experiences and actions without human intervention or reprogramming. Hence, the focus of the work is to present the readers a comprehensive survey of the applicability of machine learning and deep learning to achieve seamless navigation. The paper systematically discusses the application perspectives, research challenges, and the framework of ML (mostly) and DL (a few) based positioning approaches. The comparisons against various parameters like the technology used, the procedure applied, output metric and challenges are presented along with experimental results on benchmark datasets. The paper contributes to bridging the IO localization approaches with IO detection techniques so as to pave the way into the research domain for seamless positioning. Recent advances and hence, possible future research directions in the context of IO localization have also been articulated. • IO localization methods are presented from pragmatic view of seamless positioning. • ML techniques are categorized based on their applications in seamless positioning. • Performance results of ML techniques on benchmark datasets are reported. • The open issues along with future directions are discussed. [ABSTRACT FROM AUTHOR]

Ceramic matrix composites (CMCs) are highly promising for the hot components of the high thrust-to-weight ratio aeroengines because of their excellent high-temperature resistance and lightweight. Submillimeter cooling holes are necessary cooling structures for the extremely high working temperature of a CMCs hot component. However, CMCs are hard, brittle, and poorly conductive. Current machining is trapped in severe tool wear, poor hole quality, and low efficiency in machining such small size holes. This paper proposes high-frequency ultrasonic vibration-assisted drilling (UAD) to machine submillimeter holes of CMCs. It reveals that increasing vibration frequency during machining can enlarge the cutting edge's effective rake angle and reduce drilling forces. Correspondingly, the tool life and hole quality are improved. The machinability of high-frequency UAD is rationalized by both theoretical analysis and experiments. Results show that compared with low-frequency UAD and Conventional drilling (CD), the drilling force in high-frequency UAD is reduced by 47 % and 81 %, the tool life is more than three times, and the hole quality is improved by 12 % and 35 %, respectively. Therefore, the study paved the way for the machining of submillimeter cooling holes in CMCs, which is important to the industrial application of CMCs. [Display omitted] • The change of effective rake angle in drilling is revealed • Effects of ultrasonic vibration frequency on effective rake angle are clarified. • A drilling force model of submillimeter holes is built. • Performance of UAD in drilling small holes in CMC is demonstrated. • Effects of ultrasonic vibration frequency on drilling performance are revealed. [ABSTRACT FROM AUTHOR]

The significance of accurate short-term load forecasting (STLF) for modern power systems' efficient and secure operation is paramount. This task is intricate due to cyclicity, non-stationarity, seasonality, and nonlinear power consumption time series data characteristics. The rise of data accessibility in the power industry has paved the way for machine learning (ML) models, which show the potential to enhance STLF accuracy. This paper presents a novel hybrid ML model combining Gradient Boosting Regressor (GBR), Extreme Gradient Boosting (XGBoost), k-Nearest Neighbors (kNN), and Support Vector Regression (SVR), examining both standalone and integrated, coupled with signal decomposition techniques like STL, EMD, EEMD, CEEMDAN, and EWT. Through Automated Machine Learning (AutoML), these models are integrated and their hyperparameters optimized, predicting each load signal component using data from two sources: The National Operator of Electric System (ONS) and the Independent System Operators New England (ISO-NE), boosting prediction capacity. For the 2019 ONS dataset, combining EWT and XGBoost yielded the best results for very short-term load forecasting (VSTLF) with an RMSE of 1,931.8 MW, MAE of 1,564.9 MW, and MAPE of 2.54%. These findings highlight the necessity for diverse approaches to each VSTLF problem, emphasizing the adaptability and strength of ML models combined with signal decomposition techniques. • Novel hybrid structure of machine learning and signal decomposition approaches for VSTLF. • Combination of GBR, XGBoost, KNN, and SVR with STL, EMD, EEMD, CEEMDAN, and EWT. • Accurate predictions demonstrated for ONS and ISO-NE databases. • Valuable tool for power companies to enhance forecasting accuracy in VSTLF. • Addresses challenges of nonlinearity and non-stationarity in short-term load forecasting. [ABSTRACT FROM AUTHOR]

Abstract Wind speed and power forecast is an essential component to ensure grid stability and reliability. The traditional forecasting methods fail to address the non-linearity in the wind speed time-series, thus paving way for machine intelligent algorithms. This paper discusses a hybrid machine intelligent wind forecasting model utilizing different variants of Support Vector Regression (SVR) built on wavelet transform. Various performance indices are evaluated to identify the possible best one among four different machine learning regressors for wind forecasting application. Apart from standard ε-SVR and LS-SVR, two new regression models, namely, ε-Twin Support vector regression (ε-TSVR) and Twin Support vector regression (TSVR) are used to forecast short-term wind speed, and are compared with Persistence model for four wind farm sites. The effect of larger dataset on forecasting performance is evaluated for two wind farm sites from USA and India. Further, wind power ramp events are investigated at different hub heights and the forecasting performance of different variants of SVR is compared for five wind farm sites. Highlights • Machine intelligent SVR variants are discussed for short-term wind forecasting. • Overfitting and underfitting scenarios of variants of SVR are assessed. • Forecasting performance of SVR variants is assessed during wind power ramp event. • Wind power ramp events are analyzed at different hub heights for 5 wind farm sites. [ABSTRACT FROM AUTHOR]

The authors present the suggestive hypothesis that Romans possessed specific and specialized pavement design criteria, from which the most appropriate construction techniques and the majestic road infrastructures descend. From a back-analysis of some road pavements, it emerged that there is a good correspondence between thicknesses and materials selection used by Romans and those arising from the calculation by analytic methods introduced only in the modern age. In this paper, some considerations, from the point of view of road engineer, were presented; these could be usefully shared with the researchers in the fields of cultural heritage and archeology in order to identify both soils and road pavement materials sampling and classification systems for a new perspective of scientific speculation. [ABSTRACT FROM AUTHOR]

Taken individually, Ground Source Heat (GSH) pervious paving systems (PPS) and rainwater harvesting are not new, but in combination, this energy–water blend is relatively recent. Sealed with impermeable geomembrane, PPS becomes a water harvesting tank and by installing GSH collectors in the base, there is the potential to sustainably heat and cool buildings, provide flood resilience and improve water quality. A review of the literature found that Coefficients of Performance suggest that such systems could be considered viable, reaching the value of 2.875 required by the EU Renewable Energy Directive, 2009. Small-scale laboratory-based test rigs of the combined system were able to reduce pollutants by up to 99% for biological oxygen demand and 95% for ammonia-nitrogen, with rare occurrences of potentially pathogenic bacteria e.g. Legionella , and low survival rates of Escherichia coli . Whilst test rigs provide valuable information, field monitoring at the building scale is the only way to validate the technology. Thus, this paper presents previously unpublished results of monitoring a combined system at the building scale which found that there is clear potential to use a clean, renewable and sustainable source of heat at the same time as providing flood resilience, water quality improvements and some amenity in a domestic setting. However, it was also found that seasonal changes and building use affected levels of comfort achievable. Lessons were learnt, such as construction strategies to optimise design, including depth of the heat collectors and the optimal surface area of the PPS available to infiltrate water. [ABSTRACT FROM AUTHOR]

Pavement pre-compaction is vital for asphalt pavement construction due to its influence on the quality and service life of asphalt pavement. Conventional methods of evaluating and researching the pavement pre-compaction are based on mixture density with empirical theories, which cannot provide an understanding of asphalt-screed interaction during pre-compaction. An innovative approach is developed in this paper to evaluate pavement pre-compaction through Discrete Element Model (DEM) simulation. The contact model and input parameters were discussed and defined separately based on the real condition of paving compaction. A field test about paving compaction was conducted as well for the model validation, in the test track, the operations of paving machine can be adjusted such as paving speed, paving angle, and paving thickness. In addition, the optimized working operation was recommended in this paper based on the results from DEM simulation as well as filed test. Finally, a method to evaluate the pre-compaction of bulk materials via the average aggregate angular velocity was proposed in this study and validated through the test track, and the index Compaction Increase Ratio (CIR) was defined to compare and describe the quality of pre-compaction. [ABSTRACT FROM AUTHOR]

[Display omitted] • Three compaction methods are compared and recommended for DLPA samples. • The interlayer patterns of DLPA samples are measured and characterized. • The virtual test DLPA samples incorporate the virtual interlayer patterns. • The results of the virtual shear and pull-off tests are verified by those of real ones. • The fractal dimension can accurately predict the interlayer shear strength. The compaction method directly governs the interlayer patterns, which significantly influence the performance of asphalt pavement. The objective of this research aimed to investigate the interlayer mechanical performance of double-layer porous asphalt (DLPA) samples compacted by three methods: hot-on-cold (HoC), hot-on-warm (HoW), and hot-on-hot (HoH). The interlayer patterns at the upper-lower layer interface of DLPA samples were measured by the thin aluminum sheet and oil-saturated paper and characterized by the modified Weierstrass-Mandelbrot (W-M) function with two fractal parameters. The virtual direct shear test and pull-off test were conducted on the simulated DLPA samples incorporating interlayer patterns. The interlayer mechanical strengths from simulation were verified by laboratory experiments. The results showed that the fractal dimension and scale parameter in the modified W-M function characterized the interlayer patterns. The DLPA samples using HoH compaction exhibited the highest shear and tensile strengths that were inversely proportional to the fractal dimension, owing to the interlocking interlayer pattern generated. The HoH method was recommended to compact the DLPA pavement if the double-layer asphalt paver was available. The findings are useful to improve construction quality of the DLPA pavement. [ABSTRACT FROM AUTHOR]

Evaluating the workability of concrete pavements prior to paving can be challenging. In this paper a novel test was developed using a simplistic and economic approach to measure the response of the concrete to vibration and the ability of the concrete to hold an edge. The variability of the test was evaluated and two comparisons were made to slip formed pavers. Also, a procedure was developed using the test for comparing the workability performance of different mixtures. The procedure was used to briefly investigate the impacts of aggregate gradation on the workability of slip formed paving mixtures. [ABSTRACT FROM AUTHOR]