Search results

The purpose of this study is realizing human-like motions and performance through musculoskeletal robots and brain-inspired controllers. Human-inspired robotic systems, owing to their potential advantages in terms of flexibility, robustness and generality, have been widely recognized as a promising direction of next-generation robots.

In this paper, a deep forward neural network (DFNN) controller was proposed inspired by the neural mechanisms of equilibrium-point hypothesis (EPH) and musculoskeletal dynamics.

First, the neural mechanism of EPH in human was analyzed, providing the basis for the control scheme of the proposed method. Second, the effectiveness of proposed method was verified by demonstrating that equilibrium states can be reached under the constant activation signals. Finally, the performance was quantified according to the experimental results.

Based on the neural mechanism of EPH, a DFNN was crafted to simulate the process of activation signal generation in human motion control. Subsequently, a bio-inspired musculoskeletal robotic system was designed, and the high-precision target-reaching tasks were realized in human manner. The proposed methods provide a direction to realize the human-like motion in musculoskeletal robots.

The purpose of this study was to use bridge curvature method (BCM) to quantify stress, while multiscale modeling with adaptive coarsening predicted distortions based on experimentally validated models. Taguchi method and response surface method were used to optimize process parameters (energy density, hatch spacing, scanning speed and beam diameter).

Laser powder bed fusion (LPBF) offers significant design freedom but suffers from residual stresses due to rapid melting and solidification. This study presents a novel approach combining multiscale modeling and statistical optimization to minimize residual stress in SS316L.

Optimal parameters were identified through simulations and validated with experiments, achieving an 8% deviation. This approach significantly reduced printing costs compared to traditional trial-and-error methods. The analysis revealed a non-monotonic relationship between residual stress and energy density, with an initial increase followed by a decrease with increasing hatch spacing and scanning speed (both contributing to lower energy density). Additionally, beam diameter had a minimal impact compared to other energy density parameters.

This work offers a unique framework for optimizing LPBF processes by combining multiscale modeling with statistical techniques. The identified optimal parameters and insights into the individual and combined effects of energy density parameters provide valuable guidance for mitigating residual stress in SS316L, leading to improved part quality and performance.

The widespread use of washing machines in textile dyeing and finishing boosts product quality while leading to significant wastewater production. This wastewater poses environmental risks due to the textile industry's high pollution levels and water consumption. Sustainability hinges on minimizing water usage and treating wastewater for reuse. This study employs Matlab R2020a and Python 2023 to model experimental designs for treating textile production wastewater using the Fenton oxidation method, aiming to address sustainability concerns in the industry.

The Fenton oxidation process's efficacy and optimal operating conditions were determined through experimental sets employing the Box–Behnken design. Assessing machine learning algorithms on the data, Matlab R2020a utilized an artificial neural network (ANN), while Python 2023 employed support vector regression (SVR), decision trees (DT), and random forest (RF) models. Evaluation of model performance relied on regression coefficient (R2) and mean square error (MSE) outcomes. This methodology aimed to refine the Fenton oxidation process and identify the most efficient parameters, leveraging a combination of experimental design and advanced computational techniques across different programming platforms.

The study identified optimal conditions: pH 3, Fe+2 concentration of 0.75 g/L, and H2O2 concentration of 5 mM, yielding 87% COD removal. The Box–Behnken design achieved a high R2 of 0.9372, indicating precise predictions. Artificial neural networks (ANN) and support vector regression (SVR) exhibited successful applications, notably achieving an R2 of 0.99936 and low MSE of 0.00416 in the ANN (LOGSIG) model. However, decision trees (DT) and random forests (RF) proved less effective with limited datasets. The findings underscore technology integration in treatment modeling and the environmental imperative of wastewater purification and reuse.

This study, in which water use and wastewater treatment are evaluated with technological integration such as machine learning and data management, reveals how to contribute to targets 6, 9, 12, and 14 within the scope of UNEP 2030 sustainable development goals.

This study aims to propose an optimization framework using deep neural networks (DNN) coupled with nondominated sorting genetic algorithm II and technique for order preference by similarity to an ideal solution method to improve the tribological properties of camshaft bearing pairs of internal combustion engine.

A lubrication model based on the theory of elastohydrodynamic lubrication and flexible multibody dynamics was developed for a V6 diesel engine. Setting DNN model as fitness function, the multi-objective optimization genetic algorithm and decision-making method were used to optimize the bearing pair structure with the goal of minimizing the total friction loss and the difference of the average values of minimum oil film thickness.

The results show that the lubrication state corresponding to the optimized bearing pair structure is elastohydrodynamic lubrication. Compared with the original structure, the optimized structure significantly reduces the total friction loss.

The optimized performance and corresponding structural parameters are obtained, and the optimization results were verified through multibody dynamics simulation.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-12-2023-0417/

Stress concentration factors (SCFs) are commonly used to assess the fatigue life of tubular T-joints in offshore structures. SCFs are usually estimated from parametric equations derived from experimental data and finite element analysis (FEA). However, these equations provide the SCF at the crown and saddle points of tubular T-joints only, while peak SCF might occur anywhere along the brace. Using the SCF at the crown and saddle can lead to inaccurate hotspot stress and fatigue life estimates. There are no equations available for calculating the SCF along the T-joint's brace axis under in-plane and out-of-plane bending moments.

In this work, parametric equations for estimating SCFs are developed based on the training weights and biases of an artificial neural network (ANN), as ANNs are capable of representing complex correlations. 1,250 finite element simulations for tubular T-joints with varying dimensions subjected to in-plane bending moments and out-of-plane bending moments were conducted to obtain the corresponding SCFs for training the ANN.

The ANN was subsequently used to obtain equations to calculate the SCFs based on dimensionless parameters (α, β, γ and τ). The equations can predict the SCF around the T-joint's brace axis with an error of less than 8% and a root mean square error (RMSE) of less than 0.05.

Accurate SCF estimation for determining the fatigue life of offshore structures reduces the risks associated with fatigue failure while ensuring their durability and dependability. The current study provides a systematic approach for calculating the stress distribution at the weld toe and SCF in T-joints using FEA and ANN, as ANNs are better at approximating complex phenomena than typical data fitting techniques. Having a database of parametric equations enables fast estimation of SCFs, as opposed to costly testing and time-consuming FEA.

Workflow optimisation is crucial for establishing a viable acute stroke (AS) intervention programme in a large tertiary care centre. This study aims to utilise Lean Six Sigma (LSS) principles to enhance the hospital's workflow.

The Action Research methodology was used to implement the project and develop the case study. The study took place in a large tertiary care academic hospital in India. The Define-Measure-Analyse-Improve-Control approach optimised the workflow within 6 months. Lean tools such as value stream mapping (VSM), waste audits and Gemba were utilised to identify issues involving various stakeholders in the workflow. Sigma-level calculations were used to compare baseline, improvement and sustainment status. Additionally, statistical techniques were effectively employed to draw meaningful inferences.

LSS tools and techniques can be effectively utilised in large tertiary care hospitals to optimise workflow through a structured approach. Sigma ratings of the processes showed substantial improvement, resulting in a five-fold increase in clinical outcomes. Specifically, there was a 43% improvement in outcome for patients who underwent acute stroke revascularisation. However, certain sigma ratings deteriorated during the control and extended control (sustainment) phases. This indicates that ensuring the sustainability of quality control interventions in healthcare is challenging and requires continuous auditing.

The article presents a single case study deployed in a hospital in India. Thus, the generalisation of outcomes has a significant limitation. Also, the study encounters the challenge of not having a parallel control group, which is a common limitation in quality improvement studies in healthcare. Many studies in healthcare quality improvement, including this one, are limited by minimal data on long-term follow-up and the sustainability of achieved results.

This study pioneers the integration of LSS methodologies in a large Indian tertiary care hospital, specifically targeting AS intervention. It represents the first LSS case study applied in the stroke department of any hospital in India. Whilst most case studies discuss only the positive aspects, this article fills a critical gap by unearthing the challenges of applying LSS in a complex healthcare setting, offering insights into sustainable quality improvement and operational efficiency. This case study contributes to the theoretical understanding of LSS in healthcare. It showcases its real-world impact on patient outcomes and process optimisation.

The aim of this study was to evaluate the performance of fuel flow processes in a network of eight gas stations, located in the mesoregion of Alto Paranaíba and Triângulo Mineiro.

Two multi-criteria decision support methods were applied, respectively, of a statistical and mathematical nature, namely, Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA). The research method used was quantitative, with a brief complement of qualitative research, and descriptive in purpose, supported by the inductive method. The data collection stage took place with the support of interviews, with the application of a structured questionnaire, and non-probabilistic sampling, for convenience.

It was possible to verify that the gas station that stood out the most was station 2 (GS2), which achieved maximum efficiency, a fact that can be justified by the analysis resulting from the application of PCA, as for the product purchase variable (PP), the GS2 is the one that buys the most fuel, and is also the one with the largest storage capacity (C), and the highest volume of product sales (PS), which suggests signs of balance between supply and demand for this station, justifying its prominence.

The limitations of the study were related to the DEA technique, which requires a number of variables/indicators three times smaller than the number of DMUs considered, and the difficulty in obtaining financial data on the DMUs analyzed. Considering the security and anonymity of the gas station network, it was not possible to use this data.

The performance assessment of fuel flow processes carried out in this study promotes the efficient use of available resources as well as identifying efficient DMUs that represent benchmarks for improving management processes and performance of inefficient DMUs.

From a social perspective, this study promotes the improvement of the quality of flow processes and effective management of the fuel supply chain, ensuring the safe storage and transportation of fuels to customer supply. Performance management in this sector moves other sectors of the economy, since an efficient unit represents a balance between supply and demand, and consequently, boosts the regional economy, promoting economic growth of the population. Hiring qualified labor for this purpose also represents one of the implications of the study. From an environmental perspective, optimizing flow processes generates a reduction in greenhouse gas emissions and encourages the formulation of public policies aimed at consolidating sustainable practices.

Performance management applied to the context of the fuel supply chain is a relevant topic that has been little explored in scientific research, with a low level of information detail. This study using the inductive method allows the generalization and replication of this management pattern in other organizations in the sector in order to increase the efficiency of the fuel distribution system, with the perspective of maximizing outputs and reducing input consumption. In this aspect, the study introduces possibilities for advancement in social and environmental perspectives based on the effective management of fuel logistics.

Residing in a densely populated urban area possesses its allure; nonetheless, it can significantly impact physical and mental well-being owing to the persistent stress and information overload inherent in urban settings. This study aims to introduce a neuro-urbanism framework that can guide urban planners and designers in quantitatively evaluating individuals' responses to virtual simulated environments.

Our study consisted of two phases after randomly selecting six locations representing three types of urban areas in Bratislava, Slovakia: urban spaces, urban streets, and public parks. First, we conducted a Mentimeter live polling (dialogic survey fusion), followed by an experiment involving volunteer participants from the Slovak University of Technology. This experiment employed an electroencephalogram (EEG) with virtual reality headsets to virtually explore participants' responses to the selected locations.

The EEG signal analysis revealed significant differences in relaxation levels across the selected locations in this study. Urban streets with commercial activities promote mental well-being more effectively than public parks, challenging the preconception that restorative environments are exclusively confined to public parks.

The results demonstrate a replicable neuro-urbanism framework comprising three distinct stages: problem-based technology rooted in neuroscience, experimental setup and deliverables, and identification of restorative environments.

This paper aims to provide a new method to study and improve the dynamic characteristics of the four-column resistance strain force sensor through the elastomer structure design and optimization.

Based on the mechanism analysis method, the authors first present a dynamic characteristic model of the four-column resistance strain force sensors’ elastomer. Then, the authors verified and modified the model according to the Solidworks finite element simulation results. Finally, the authors designed and optimized two types of four-column elastomers based on the dynamic characteristic model and verified the improvement of sensor dynamic performance through a hammer knock dynamic experiment.

The Solidworks finite element simulation and hammer knock dynamic experiment results show that the relative error of the model is less than 10%, which confirms the accuracy of the model. The dynamic performance of the sensors based on the model can be improved by more than 30%, which is a great improvement in sensor dynamic performance.

The authors first present a dynamic characteristic model of the four-column elastomer and optimize the four-column sensors successfully based on the mechanism analysis method. And a new method to study and improve the dynamic characteristics of the resistance is provided.

This paper delves into the aerodynamic optimization of a single-stage axial turbine employed in aero-engines.

An efficient integrated design optimization approach tailored for turbine blade profiles is proposed. The approach combines a novel hierarchical dynamic switching PSO (HDSPSO) algorithm with a parametric modeling technique of turbine blades and high-fidelity Computational Fluid Dynamics (CFD) simulation analysis. The proposed HDSPSO algorithm introduces significant enhancements to the original PSO in three pivotal aspects: adaptive acceleration coefficients, distance-based dynamic neighborhood, and a switchable learning mechanism. The core idea behind these improvements is to incorporate the evolutionary state, strengthen interactions within the swarm, enrich update strategies for particles, and effectively prevent premature convergence while enhancing global search capability.

Mathematical experiments are conducted to compare the performance of HDSPSO with three other representative PSO variants. The results demonstrate that HDSPSO is a competitive intelligent algorithm with significant global search capabilities and rapid convergence speed. Subsequently, the HDSPSO-based integrated design optimization approach is applied to optimize the turbine blade profiles. The optimized turbine blades have a more uniform thickness distribution, an enhanced loading distribution, and a better flow condition. Importantly, these optimizations lead to a remarkable improvement in aerodynamic performance under both design and non-design working conditions.

These findings highlight the effectiveness and advancement of the HDSPSO-based integrated design optimization approach for turbine blade profiles in enhancing the overall aerodynamic performance. Furthermore, it confirms the great prospects of the innovative HDSPSO algorithm in tackling challenging tasks in practical engineering applications.