Search results

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

The purpose of this study is to realize the multi-objective optimization for MRR and surface roughness in micro-milling of Inconel 718.

Taguchi method has been applied to conduct experiments, and the cutting parameters are spindle speed, feed per tooth and depth of cut. The first-order models used to predict surface roughness and MRR for micro-milling of Inconel 718 have been developed by regression analysis. Genetic algorithm has been utilized to implement multi-objective optimization between surface roughness and MRR for micro-milling of Inconel 718.

This paper implemented the multi-objective optimization between surface roughness and MRR for micro-milling of Inconel 718. And some conclusions can be summarized. Depth of cut is the major cutting parameter influencing surface roughness. Feed per tooth is the major cutting parameter influencing MRR. A number of cutting parameters have been obtained along with the set of pareto optimal solu-tions of MRR and surface roughness in micro-milling of Inconel 718.

There are a lot of cutting parameters affecting surface roughness and MRR in micro-milling, such as tool diameter, depth of cut, feed per tooth, spindle speed and workpiece material, etc. However, to the best our knowledge, there are no published literatures about the multi-objective optimization of surface roughness and MRR in micro-milling of Inconel 718.

In the continuous development of high-speed railways, ensuring the safety of the operation control system is crucial. Electromagnetic interference (EMI) faults in signaling equipment may cause transportation interruptions, delays and even threaten the safety of train operations. Exploring the impact of disturbances on signaling equipment and establishing evaluation methods for the correlation between EMI and safety is urgently needed.

This paper elaborates on the necessity and significance of studying the impact of EMI as an unavoidable and widespread risk factor in the external environment of high-speed railway operations and continuous development. The current status of research methods and achievements from the perspectives of standard systems, reliability analysis and safety assessment are examined layer by layer. Additionally, it provides prospects for innovative ideas for exploring the quantitative correlation between EMI and signaling safety.

Despite certain innovative achievements in both domestic and international standard systems and related research for ensuring and evaluating railway signaling safety, there’s a lack of quantitative and strategic research on the degradation of safety performance in signaling equipment due to EMI. A quantitative correlation between EMI and safety has yet to be established. On this basis, this paper proposes considerations for research methods pertaining to the correlation between EMI and safety.

This paper overviews a series of methods and outcomes derived from domestic and international studies regarding railway signaling safety, encompassing standard systems, reliability analysis and safety assessment. Recognizing the necessity for quantitatively describing and predicting the impact of EMI on high-speed railway signaling safety, an innovative approach using risk assessment techniques as a bridge to establish the correlation between EMI and signaling safety is proposed.

Accurate glide path tracking is vital to the automatic carrier landing task of unmanned aerial vehicle (UAV). The purpose of this paper is to develop a reliable flight controller that can simultaneously deal with external disturbance, structure fault and actuator fault.

The automatic carrier landing task is resolved into the glide path tracking problem and attitude tracking problem. The disturbance observer-based adaptive sliding mode control scheme is proposed for system stabilization, disturbance rejection and fault tolerance.

Both the Lyapunov method and exemplary simulations can prove that the disturbance estimation error and the attitude tracking error converge in finite time in the presence of external disturbances and various faults.

The presented algorithm is testified by a UAV automatic carrier landing simulation, which shows the potential of practical usage.

The barrier function is introduced to adaptively update both the sliding mode observer gain and sliding mode controller gain, so that the sliding mode surface could converge to a predefined region without overestimation. The proposed flight controller ensures a secure carrier landing task.

Online platforms are providing diversified and personalized services with user information. Users should decide if they should give up parts of information for convenience, with their information being at the risk of being illegally collected, leaked, spread and misused. This study aims to explore the main factors influencing users' online information disclosure intention from the perspectives of privacy, technology acceptance and trust, and the authors extend previous research with two moderators.

Based on 48 independent empirical studies, this paper conducted a meta-analysis to synthesize existing results from collected individual studies. This meta-analysis explored the main factors influencing users' online information disclosure intention from the perspectives of privacy, technology acceptance and trust.

The meta-analysis results based on 48 independent studies revealed that perceived benefit, trust, subjective norm and perceived behavioral control have significant positive effects, while perceived privacy risk and privacy concern have significant negative effects. Moreover, cultural background and platform type moderate the relationship between antecedents and online information disclosure intention.

This paper explored the moderating effects of an individual factor and a platform factor on users' online information disclosure intention. The moderating effect of cultural differences is examined with Hofstede's dimensions, and the moderating role of the purpose of online information disclosure is examined with platform type. This study extends online information disclosure literature with a multi-perspective meta-analysis and provides guidelines for practitioners.

The purpose of this paper is to focus on determining the optimal sales price for non-instantaneous deterioration items according to consideration of freshness and demand.

In this model, the authors have described the demand function which is dependent on price as well time. The products that the deterioration is considered as non-instantaneous have a determinate shelf life, and their demand rate will decrease over time after the beginning of the selling period. This paper depicts that the total profit of non-instantaneous deterioration items using the dynamic pricing strategy is higher than that using fixed pricing strategy.

Finally, to illustrate and validate the model, the authors have used some numerical examples. A new freshness function and the model to study pricing policy are developed as well applied to solve managerial decision problems.

This paper complements the lack of the existing theoretical research of pricing for non-instantaneous deterioration items under an e-commerce environment. A new freshness function and the model to study pricing policy are developed as well applied to solve managerial decision problems.

Artificial intelligence (AI) is experiencing growth and prosperity worldwide because of its convenience and other benefits. However, AI faces challenges related to consumer resistance. Thus, drawing on the user resistance theory, this study explores factors that influence consumers’ resistance to AI and suggests ways to mitigate this negative influence.

This study tested four hypotheses across four studies by conducting lab experiments. Study 1 used a questionnaire to verify the hypothesis that AI’s “substitute” image leads to consumer resistance to AI; Study 2 focused on the role of perceived threat as an underlying driver of resistance to AI. Studies 3–4 provided process evidence by the way of a measured moderator, testing whether AI with servant communication style and literal language style is resisted less.

This study showed that AI’s “substitute” image increased users' resistance to AI. This occurs because the substitute image increases consumers’ perceived threat. The study also found that using servant communication and literal language styles in the interaction between AI and consumers can mitigate the negative effects of AI-substituted images.

This study reveals the mechanism of action between AI image and consumers’ resistance and sheds light on how to choose appropriate image and expression styles for AI products, which is important for lowering consumer resistance to AI.

Advertisements for dietary supplements (DS) often include misleading claims regarding their health benefits. In this study, the authors designed an online advertisement for plant-based DS featuring misleading claims and investigated its effects on mature Chinese consumers before and after revealing the false claims. A consumer involvement framework was developed to evaluate the mediating effect of advertising involvement (AI) on the correlation between product involvement (PI), situational involvement (SI) and purchase intention (PI).

A total of 467 mature adults aged over 40 years who resided in China's Yangtze River Delta region and had experience in purchasing DS online were recruited. Relevant data were collected through an online survey and analysed through structural equation modelling.

Cognitive PI was positively correlated with both SI and PI and SI was positively correlated with PI. AI negatively moderated the correlation between affective PI and SI. Both cognitive PI and AI were positively correlated with PI and the correlation was mediated through SI.

DS consumption is a rational decision-making process driven by utilitarian motives. Consumers who are aware of the misleading claims adopt a cautious evaluation approach and place themselves in specific purchase situations before making a purchase decision. This study advances the literature by incorporating the consideration of misleading advertisements into the consumer involvement model within the context of online DS consumption. The study's findings provide insights to intensify monitoring of false advertisements in the DS industry and design effective consumer education programmes.

This study aims to identify profiles of inclusion in the workplace to provide evidence-based guidance to build an inclusive organization.

Latent profile analysis (LPA), a person-centred classification analytical tool, was applied to determine the subtypes of inclusion with Mplus 7.4, using two-wave data collected from 368 employees in 8 Chinese companies.

Three subgroups were identified: identity inclusion group (the highest level of inclusion, 34.0%), value inclusion group (the moderate level of inclusion, 47.5%) and low inclusion group (the lowest level of inclusion, 18.5%). The findings indicate that groups with male, aged and highly educated members, as well as members from developed areas generally tend to feel more included and greater inclusion relates to more favourable outcomes and fewer detrimental consequences.

As this study was conducted only in China, the results may not be generalizable to non-Chinese contexts.

The results may help organizational leaders develop a deeper understanding of the significance and the crux of inclusion. To address the duality of workforce diversity, managers can take initiatives to create an inclusive organization. To achieve inclusion, managers should pay attention to ways of improving the perceptions of inclusion among all employees.

This is among the first studies to identify the variants in inclusion in China using LPA. It reveals the subtypes and characteristics of inclusion and can serve as a starting point to explore how to realize organizational inclusion in theory and practice.