Explore the vast range of titles available.

Compressed-air energy storage (CAES) is considered a promising energy storage system for many grid applications, including managing renewable variability and grid capacity concerns. However, compared with conventional generation such as coal or hydro, the cost of storage power of CAES is still high, which impedes its deployment. Therefore a standing question is how to operate CAES in the most efficient and economical fashion, that is, to exploit the system functions for maximum-possible benefit. This study investigates the CAES dynamic reactive capability used to stabilise wind farms under grid fault conditions. Two considered operation modes are motor mode with leading power factor and synchronous condenser mode. Analysis with a 60-MW wind farm and two types of popular wind turbines, namely stall-regulated and doubly fed induction-generator-based WTs, shows that the CAES performance is comparable or better than that of an static var compensator in most situations investigated. Therefore the reactive-power-supply function should be considered in CAES design and operation to increase the system efficiency and value.

Compressive strength of concrete is one of the most determinant parameters in the design of engineering structures. This parameter is generally determined by conducting several tests at different ages of concrete in spite of the fact that such tests are not only costly but also time-consuming. As an alternative to these tests, machine learning (ML) techniques can be used to estimate experimental results. However, the dependence of compressive strength on different parameters in the fabrication of concrete makes the prediction problem challenging, especially in the case of concrete with partial replacements for cement. In this investigation, an extreme learning machine (ELM) is combined with a metaheuristic algorithm known as grey wolf optimizer (GWO) and a novel hybrid ELM-GWO model is proposed to predict the compressive strength of concrete with partial replacements for cement. To evaluate the performance of the ELM-GWO model, five of the most well-known ML models including an artificial neural network (ANN), an adaptive neuro-fuzzy inference system (ANFIS), an extreme learning machine, a support vector regression with radial basis function (RBF) kernel (SVR-RBF), and another SVR with a polynomial function (Poly) kernel (SVR-Poly) are developed. Finally, the performance of the models is compared with each other. The results of the paper show that combining the ELM model with GWO can efficiently improve the performance of this model. Also, it is deducted that the ELM-GWO model is capable of reaching superior performance indices in comparison with those of the other models.

Accurate prediction of ground vibration caused by blasting has always been a significant issue in the mining industry. Ground vibration caused by blasting is a harmful phenomenon to nearby buildings and should be prevented. In this regard, a new intelligent method for predicting peak particle velocity (PPV) induced by blasting had been developed. Accordingly, 150 sets of data composed of thirteen uncontrollable and controllable indicators are selected as input dependent variables, and the measured PPV is used as the output target for characterizing blast-induced ground vibration. Also, in order to enhance its predictive accuracy, the gray wolf optimization (GWO), whale optimization algorithm (WOA) and Bayesian optimization algorithm (BO) are applied to fine-tune the hyper-parameters of the extreme gradient boosting (XGBoost) model. According to the root mean squared error (RMSE), determination coefficient (R2), the variance accounted for (VAF), and mean absolute error (MAE), the hybrid models GWO-XGBoost, WOA-XGBoost, and BO-XGBoost were verified. Additionally, XGBoost, CatBoost (CatB), Random Forest, and gradient boosting regression (GBR) were also considered and used to compare the multiple hybrid-XGBoost models that have been developed. The values of RMSE, R2, VAF, and MAE obtained from WOA-XGBoost, GWO-XGBoost, and BO-XGBoost models were equal to (3.0538, 0.9757, 97.68, 2.5032), (3.0954, 0.9751, 97.62, 2.5189), and (3.2409, 0.9727, 97.65, 2.5867), respectively. Findings reveal that compared with other machine learning models, the proposed WOA-XGBoost became the most reliable model. These three optimized hybrid models are superior to the GBR model, CatB model, Random Forest model, and the XGBoost model, confirming the ability of the meta-heuristic algorithm to enhance the performance of the PPV model, which can be helpful for mine planners and engineers using advanced supervised machine learning with metaheuristic algorithms for predicting ground vibration caused by explosions.

Recycled aggregate concrete is used as an alternative material in construction engineering, aiming to environmental protection and sustainable development. However, the compressive strength of this concrete material is considered as a crucial parameter and an important concern for construction engineers regarding its application. In the present work, the 28-days compressive strength of recycled aggregate concrete is investigated through four artificial intelligence techniques based on a meta-heuristic search of sociopolitical algorithm (i.e. ICA) and XGBoost, called the ICA-XGBoost model. Based on performance indices, the optimum among these developed models proved to be ICA-XGBoost model. Namely, findings demonstrated that the proposed ICA-XGBoost model performed better than the other models (i.e. ICA-ANN, ICA-SVR, and ICA-ANFIS models) in estimating compressive strength of recycled aggregate concrete. The suggested model can be used in construction engineering in order to ensure adequate mechanical performance of the recycled aggregate concrete and allow its safe use for building purposes.

Forging is a traditional and important manufacturing technology to produce various high strength products and is widely used in engineering fields such as automotive, aerospace and heavy industry. To produce highly accurate product, underfill that the material is not filled into the cavity should strongly avoided. For material saving and near-net product, flash should be minimized. To make the tool life long, it is preferable to produce product with low forging load. It is also preferable to uniformly deform the billet as much as possible for high strength product. Crack is a crucial defect and should strongly be avoided. Therefore, many requirements are taken into account in order to produce the forged product. To meet the requirements, design optimization in forging coupled with computer aided engineering (CAE) is an effective approach. This paper systematically reviews the related papers from the design optimization point of view. For the billet or die shape optimization, the papers are classified into four approaches. The process parameters optimization such as the billet temperature, the die temperature, the stroke length and the friction coefficient is conducted, and the related papers are also classified into four categories. The design variables and the objective function(s) used in the papers are clarified with the design optimization technique. The multi-stage forging including the hammer forging for producing complex product shape is also briefly reviewed. Finally, major performance indexes and the future outlook are summarized for the further development of design optimization in forging.

The increasing interest in wearable smart healthcare systems has sparked considerable attention toward flexible sensors owing to their high sensitivity and flexibility. However, these sensors still face challenges in terms of performance imbalances and instability. To address these issues, graphene-based conductive materials with exceptional mechanical and electrical properties have been incorporated into flexible sensors. Despite the potential of graphene, a comprehensive understanding of the sensing mechanisms and influence of fabrication methods on the performance of graphene-based flexible sensors is lacking. This article aims to bridge this gap by providing an overview of the latest research progress in flexible graphene sensors. We begin by analyzing the main properties of graphene materials, including tensile strength, specific surface area, thermal conductivity, and electrical conductivity. These properties highlight the superior characteristics of graphene for flexible sensor applications. The sensing mechanisms of strain/pressure, gas, and temperature flexible sensors are reviewed, with a focus on innovations in graphene composites, regular microstructures, and emerging preparation methods that enable an effective balance of the individual properties of a single flexible sensor. Furthermore, the article discusses graphene-based multifunctional flexible sensors that allow for the simultaneous monitoring of multiple stimuli, self-powered performance studies, and wireless communication performance studies. Performance analysis of these sensors in the context of flexible systems is provided. Finally, this article presents a comprehensive summary of flexible graphene sensors and offers an outlook for the future. We aim to provide theoretical guidance and technical support for the realization of individual whole-life physical sign detection using flexible graphene-based sensors.

This paper proposes a new approach based on an unsupervised deep learning (DL) model for landslide detection. Recently, supervised DL models using convolutional neural networks (CNN) have been widely studied for landslide detection. Even though these models provide robust performance and reliable results, they depend highly on a large labeled dataset for their training step. As an alternative, in this paper, we developed an unsupervised learning model by employing a convolutional auto-encoder (CAE) to deal with the problem of limited labeled data for training. The CAE was used to learn and extract the abstract and high-level features without using training data. To assess the performance of the proposed approach, we used Sentinel-2 imagery and a digital elevation model (DEM) to map landslides in three different case studies in India, China, and Taiwan. Using minimum noise fraction (MNF) transformation, we reduced the multispectral dimension to three features containing more than 80% of scene information. Next, these features were stacked with slope data and NDVI as inputs to the CAE model. The Huber reconstruction loss was used to evaluate the inputs. We achieved reconstruction losses ranging from 0.10 to 0.147 for the MNF features, slope, and NDVI stack for all three study areas. The mini-batch K-means clustering method was used to cluster the features into two to five classes. To evaluate the impact of deep features on landslide detection, we first clustered a stack of MNF features, slope, and NDVI, then the same ones plus with the deep features. For all cases, clustering based on deep features provided the highest precision, recall, F1-score, and mean intersection over the union in landslide detection.

This work describes the advancement in developing a cable-driven gear transmission joint designed as a basic element for a long-reach hyper-redundant robot. Hyper-redundancy allows the robot to perform auxiliary tasks such as obstacle avoidance and joint limits satisfaction. This feature makes hyper-redundant robots particularly useful for performing tasks in confined and hazardous environments and areas that are not reachable by a human operator. The long-reach feature of the robot requires a detailed study of the overall structure and its components. The joint must be capable of transmitting forces and movements over a long distance without losing the precision and accuracy of the end-effector, so it is designed to optimise the robot’s performance in terms of stiffness, structural resistance, and functional characteristics. In light of the above considerations, the main focus of this work is to improve the structural performance of the entire robotic system. Consequently, since the most critical component of the robot in terms of torsional deformation is the gear transmission joint, this paper aims to design a torsional stiffener element to reduce its deformation and, thus, an increase of torsional stiffness of the overall robotic system. Tube-shaped and rectangular-shaped stiffener elements, which can fit the joint design satisfying its geometrical constraints, are proposed. A computer-aided engineering approach is implemented to improve the precision of positioning of the end-effector by adding stiffener elements in the joint. Two sensitivity analyses, varying the geometry of the proposed stiffener elements, are performed to evaluate their performance in terms of added mass and displacement reduction.

Engineering design research integrating artificial intelligence (AI) into computer-aided design (CAD) and computer-aided engineering (CAE) is actively being conducted. This study proposes a deep learning-based CAD/CAE framework in the conceptual design phase that automatically generates 3D CAD designs and evaluates their engineering performance. The proposed framework comprises seven stages: (1) 2D generative design, (2) dimensionality reduction, (3) design of experiment in latent space, (4) CAD automation, (5) CAE automation, (6) transfer learning, and (7) visualization and analysis. The proposed framework is demonstrated through a road wheel design case study and indicates that AI can be practically incorporated into an end-use product design project. Engineers and industrial designers can jointly review a large number of generated 3D CAD models by using this framework along with the engineering performance results estimated by AI and find conceptual design candidates for the subsequent detailed design stage.

In this paper, for the first time, the role of manufacturing parameters of fused deposition modeling (FDM) on the shape memory effect (SME) is investigated by design of experiments. PLA-TPU blend with a weight composition of 30:70% is processed by melt mixing and then extruded into 1.75 mm filaments for 3D printing via FDM. SEM images reveal that TPU droplets are distributed in the PLA matrix, and the immiscible matrix-droplet morphology is evident. Box-Behnken design (BBD), as an experimental design of the response surface method (RSM), is implemented to fit the model between variables and responses. The shell, infill density, and nozzle temperature are selected as variables, and their effects on loading stress, recovery stress, shape fixity, and shape recovery ratio are studied in detail. An analysis of variance (ANOVA) is applied to estimate the importance of each printing parameter on the output response and assess the fitness of the presented model. The ANOVA results reveal the high accuracy of the model and the importance of the parameters. Infill density and nozzle temperature had the greatest and least roles on shape memory properties, respectively. Also, the values of shape fixity and shape recovery were obtained in the ranges of 58–100% and 53–91%, respectively. Despite many researches on 4D printing of PLA, low ductility at room temperature and high stress relaxation rate are its weakness, which are covered by adding TPU in this research. Due to the lack of similar outcomes in the specialized literature, this paper is likely to fill the gap in the state-of-the-art problem and supply pertinent data that are instrumental for FDM 3D printing of functional shape memory polymers with less material consumption.