Search results

The current studies on remaining useful life (RUL) prediction mainly rely on convolutional neural networks (CNNs) and long short-term memories (LSTMs) and do not take full advantage of the attention mechanism, resulting in lack of prediction accuracy. To further improve the performance of the above models, this study aims to propose a novel end-to-end RUL prediction framework, called convolutional recurrent attention network (CRAN) to achieve high accuracy.

The proposed CRAN is a CNN-LSTM-based model that effectively combines the powerful feature extraction ability of CNN and sequential processing capability of LSTM. The channel attention mechanism, spatial attention mechanism and LSTM attention mechanism are incorporated in CRAN, assigning different attention coefficients to CNN and LSTM. First, features of the bearing vibration data are extracted from both time and frequency domain. Next, the training and testing set are constructed. Then, the CRAN is trained offline using the training set. Finally, online RUL estimation is performed by applying data from the testing set to the trained CRAN.

CNN-LSTM-based models have higher RUL prediction accuracy than CNN-based and LSTM-based models. Using a combination of max pooling and average pooling can reduce the loss of feature information, and in addition, the structure of the serial attention mechanism is superior to the parallel attention structure. Comparing the proposed CRAN with six different state-of-the-art methods, for the predicted results of two testing bearings, the proposed CRAN has an average reduction in the root mean square error of 57.07/80.25%, an average reduction in the mean absolute error of 62.27/85.87% and an average improvement in score of 12.65/6.57%.

This article provides a novel end-to-end rolling bearing RUL prediction framework, which can provide a reference for the formulation of bearing maintenance programs in the industry.

The purpose of this study is to investigate how consumer brand engagement (CBE) promotes brand love and eWOM within the influence of brand interactivity and consumer involvement, especially in the context of the smartphone industry and Chinese social media marketing. This study also examines the important role of brand love and gender in this relationship.

Data from 403 participants who are followers of the smartphone brand’s social media page was collected via an online survey. PLS-SEM was also used for examining the research model.

The findings of this research reveal that the (perceived) brand interactivity, and consumer involvement, are key factors influence CBE. As expected, brand love and consumers’ eWOM intention are significant outcomes of CBE. In particular, the relationship between CBE and consumers’ eWOM intention is mediated by brand love. However, gender did not moderate the proposed relationships.

By integrating social exchange theory and attribution theory, this study deepens the understanding of CBE and brand love by examining the relationship between brand interactivity, consumer involvement, CBE, brand love and eWOM in the context of smartphone and Chinese social media marketing.

The purpose of this paper is to assess the risk of controlled flight into terrain (CFIT) for airlines and to develop a practical method for evaluating and predicting CFIT risk to ensure safe and efficient airline operations.

In accordance with the monitoring project specification issued by the Flight Standards Department of the Civil Aviation Administration of China (CAAC), a preliminary draft of evaluation indicators for CFIT risk was developed based on the literature review and semi-structured interviews. Fifteen aviation experts were then selected and invited to participate in a Delphi method to revise the draft. Analytic hierarchy process (AHP) and entropy weight method were used to determine the combined weight of the indicators. The variable fuzzy set model and quick access recorder (QAR) data were applied to evaluate the CFIT risk of an airline from 2007 to 2018, and the classification results were compared with actual operational data.

The research findings reveal that the six most significant monitoring items affecting CFIT risk are incorrect configuration settings during landing, loss of altitude during climbing, ground proximity warning, G/S deviation, flap extension delay during landing and incorrect takeoff configuration. The CFIT risk of airlines has shown an increasing trend since 2015. The values in 2010, 2017 and 2018 were greater than 2 and less than 2.5, indicating that the CFIT risk is at Level 2, close to Level 3, and the risk is low but approaching medium.

Using the combination weight determined by AHP and entropy weight method to rank the weight of 15 monitoring items, airlines can take necessary measures (simulator training, knowledge training) to reduce the occurrence of monitoring items with high weight to reduce CFIT risk. This risk assessment method can quantitatively evaluate the CFIT risk of airlines and provide theoretical guidance and technical support for airlines to formulate safety management measures and flight training programs, enabling the interconnection between QAR data and flight quality.

The proposed method in this study differs from traditional approaches by offering a quantitative assessment of CFIT risk for airlines and enabling the interconnection between QAR data and flight quality.

While the relationship between non-family CEOs and corporate innovation in China has been widely studied, the results remain inconclusive. This study explores the relationship between non-family CEOs and corporate innovation in the context of intergenerational succession. It considers the background and background characteristics of non-family CEOs in an attempt to provide a theoretical foundation for human resource management and innovative strategic management that can be applied in the transformation of family companies.

The authors develop, then test, a series of hypotheses using an econometric analysis of a large sample of Chinese listed family firms. To control for endogeneity problems, such as missing variables in the model and the selectivity bias of the sample, propensity score matching (PSM) model is applied to analyze the panel data of 452 listed family firms from 2009–2019.

This study first validates the mechanism by which non-family CEO background characteristics affect innovation performance in family firms. It then reveals the varying moderating effects of two stages of intergenerational succession (i.e. later-generation participation in management and later-generation take-over management) that influence the relationship between non-family CEOs and corporate innovation.

The study's findings based on upper echelon and imprinting theory complement and extend existing research by revealing the impact of non-family CEOs from different backgrounds, and also identifying the role of intergenerational succession in the relationship between non-family CEO background characteristics and innovation performance.

Hydrodynamic parameter estimation is significant for the velocity prediction of unmanned surface vehicles. Considering the field data’s uncertain nonlinearities (environmental disturbances and measurement noise), this paper aims to propose a hybrid adaptive parameter estimation (HAPE) strategy.

First, a rough estimation of hydrodynamic parameters is used by the least squares method. Second, an improved adaptive parameter estimation algorithm is applied to compensate for the influence of uncertain nonlinearities and adjust the parameters within the rough range. Finally, it is proved that the calculated velocity asymptotically converges to the actual value during the parameter estimation procedure.

The numerical simulation and pool experiments are conducted in two scenarios of steady turning and sinusoidal thrust to verify the effectiveness of the proposed HAPE method. The results validate that the accuracy of the predicted velocity using the hydrodynamic model obtained by the HAPE strategy is better than the APE algorithm. In addition, the hydrodynamic parameters estimated with the sinusoidal thrust data are more applicable than the steady turning data.

This study proposes a HAPE strategy that considers the uncertain nonlinearities of the field data. This method provides a more accurate predicted velocity. Besides, as far as we know, it is the first time to analyze the influence of different test conditions on the accuracy of the predicted velocity.

Products that espouse environmental ethical principles have received increasing attention in recent years. However, one key barrier against sustainable consumption is that green attributes could result in consumer’s expectation of decreased product physical performance. This study aims to investigate how green attributes existing in different product categories affect consumer purchase intention.

Two experimental studies were conducted to test the hypotheses. Study 1 provides initial evidence of the interaction effects between green attributes and product category on consumer purchase intention. Study 2 replicates the findings of Study 1 and further tests a benefits-based mechanism in the relationship between green attributes and consumer purchase intention.

The findings show that in the utilitarian product category, products with green peripheral attributes result in a higher purchase intention than those with green core attributes, whereas, in the hedonic product category, products with green core attributes result in a higher purchase intention than those with green peripheral attributes. Furthermore, the authors demonstrate that green attributes, as universal sustainability cues predominantly affect consumers’ perceptions of utilitarian environmental benefits and self-expression benefits, which further enhance their purchase intention towards utilitarian products and hedonic products, respectively.

This study responds to the calls for more empirical studies into discussing the role of green attributes in consumer purchase intention. Furthermore, it uncovers a benefits-based mechanism that explains how green attributes existing in utilitarian product categories and hedonic product categories trigger consumers’ analysis of benefits, leading to positive consumer purchase intention.

The purpose of this study is to optimize and improve conventional welding using EMF assisted technology. Current industrial production has put forward higher requirements for welding technology, so the optimization and improvement of traditional welding methods become urgent needs.

External magnetic field assisted welding is an emerging technology in recent years, acting in a non-contact manner on the welding. The action of electromagnetic forces on the arc plasma leads to significant changes in the arc behavior, which affects the droplet transfer and molten pool formation and ultimately improve the weld seam formation and joint quality.

In this paper, different types of external magnetic fields are analyzed and summarized, which mainly include external transverse magnetic field, external longitudinal magnetic field and external cusp magnetic field. The research progress of welding behavior under the effect of external magnetic field is described, including the effect of external magnetic field on arc morphology, droplet transfer and weld seam formation law.

However, due to the extremely complex physical processes under the action of the external magnetic field, the mechanism of physical fields such as heat, force and electromagnetism in the welding has not been thoroughly analyzed, in-depth theoretical and numerical studies become urgent.

The modeling and optimization of a weld bead in the middle of the weld are often simple, as the forming process is dynamically balanced. However, the arc striking (AS) and arc extinguishing (AE) areas of weld beads are generally abnormal because the dynamic processes at these areas are unstable. The purpose of this paper is to investigate the abnormal areas of the weld bead with optimization modeling methods in wire and arc additive manufacturing (WAAM).

A burning-back method was proposed to fill the slanted plane in the AE area. To optimize the welding parameters and obtain the optimal design, a response surface methodology was proposed to build the relationships between the input parameters and response variables.

The proposed burning-back method could fill the slanted plane in the AE area. Second-order models of abnormal areas were developed and the optimization effects were analyzed. The experimental results indicated that the relationship models at both ends were applicable and preferable for the optimization of weld beads.

In this paper, a burning-back method was proposed to optimize the slanted plane in the AE area. Second-order models of abnormal areas were established. The methods and models were preferable in the optimization of the abnormal areas in WAAM.

This paper aims to study whether rural collective construction land marketization (RCCLM) affects pension industry and analyze its impact mechanism.

Based on the theory of planned behavior (TPB) and social cognition theory (SCT), this paper constructs a theoretical framework for the purchase behavior of rural retirement housing with the influence of RCCLM. A mixed-methods investigation combining qualitative and quantitative study is adopted in this paper.

The research results indicate that the purchase intention of rural retirement housing has a significant positive impact on the purchase behavior. However, RCCLM has a significant negative impact on the purchase intention of rural retirement housing. A logical framework of “land system participant behavior” has been constructed from three main bodies: government, developers and elderly urban and rural residents.

This paper provides suggestions for the three entities from the perspectives of macro, medium and micro-level to improve transaction system for rural collective construction land use right (TSRCCLUR), providing references for the collective construction land marketization policy and the development of the pension industry.

This paper deepens the study of behavior intention in planned behavior, enriches TPB model in the study of rural retirement housing security and clarifies the influence mechanism of the rural retirement housing purchase intention with the theoretical and empirical test of the model.

This paper aims to investigate, upon taking into consideration both symmetric and asymmetric effects, how the economic and psychological impact of the coronavirus disease 2019 (COVID-19) pandemic, solidarity and future anxiety affect travel intention and the willingness to support a destination (WSD). Furthermore, the study sheds light on whether these relationships vary between domestic and international destinations.

The data are collected from 379 potential tourists. To detect and analyze the symmetrical and asymmetric effects, the covariance-based structural equation modeling (CB-SEM) and the fuzzy-set qualitative comparative analysis (fsQCA) are employed, respectively.

It is observed that, whereas only the effects of solidarity on travel intention and WSD differ in the CB-SEM, the fsQCA results include different recipes for the two groups.

There has not been much research done yet on the influence of future anxiety on tourists' decisions. Furthermore, it has not been thoroughly investigated whether solidarity has a different function for destinations within and outside of the country. In this respect, the study of both symmetric and asymmetric effects represents an important contribution to the literature.