Search results

Rotating machinery is a crucial component of large equipment, and detecting faults in it accurately is critical for reliable operation. Although fault diagnosis methods based on deep learning have been significantly developed, the existing methods model spatial and temporal features separately and then weigh them, resulting in the decoupling of spatiotemporal features.

The authors propose a spatiotemporal long short-term memory (ST-LSTM) method for fault diagnosis of rotating machinery. The authors collected vibration signals from real rolling bearing and gearing test rigs for verification.

Through these two experiments, the authors demonstrate that machine learning methods still have advantages on small-scale data sets, but our proposed method exhibits a significant advantage due to the simultaneous modeling of the time domain and space domain. These results indicate the potential of the interactive spatiotemporal modeling method for fault diagnosis of rotating machinery.

The authors propose a ST-LSTM method for fault diagnosis of rotating machinery. The authors collected vibration signals from real rolling bearing and gearing test rigs for verification.

Building on social media and destination brand-related literature, this study aims to explore World Heritage Sites’ (WHSs) brand diffusion and formation process from long-term and short-term perspectives, which includes brand diffusion, user-generated content (UGC), opinion leaders and brand events’ impact.

This study uses a mixed-method including text mining, keyword analysis and social network analysis to explore the brand formation process of four popular WHSs in Beijing, namely, the Palace Museum, Great Wall, Summer Palace and Temple of Heaven and more than 10,000,000 users’ data on Sina Weibo has been implemented to uncover the underlying social media branding mechanism.

The results show that the number of postings keeps in a stable range in most months, but, in general, there are no common rules for changing trends among the four WHSs; long-term high-frequency keywords related to history and culture account for a higher percentage; different kinds of accounts have varying impacts on information diffusion, in which media accounts lead to a bigger influence. However, more followers do not necessarily mean more interactions and most of the interaction ratio is much lower than 0.01000; brand events facilitate brand dissemination and have an impact on the creation of UGC.

This study is valuable for destination marketers to deeper understand brand diffusion and formation and provides valuable insights for developing effective destination marketing strategies.

Unlike previous studies that only concern a few parts of destination brand formation via social media (e.g. brand diffusion, brand events or opinion leaders’ impact), this study takes a more comprehensive perspective by systematically analyzing the brand formation process of WHSs on social media. By considering both long-term diffusion and short-term representative events, this study provides a more holistic understanding of the branding mechanism.

Green technology innovation is the organic combination of green development and innovation driven. It is also a powerful guarantee for shaping sustainable competitive advantages of manufacturing enterprises. To explore what kind of executive incentive contracts can truly stimulate green technology innovation, this study aims to distinguish the equity incentive and reputation incentive, upon their contractual elements characteristics and green governance effects, and then put forward suggestions for green technology innovation accordingly.

This study establishes an evaluation model and uses empirical methods to test. Concretely, using data from A-share listed manufacturing companies for the period from 2007 to 2020, this study compares and analyzes the impact of equity and reputation incentive on green technology innovation and explores the relationship between internal green business behavior and external green in depth.

This study finds that reputation incentives focus on long-term and non-utilitarian orientation, which can promote green technology innovation in enterprises. While equity incentives, linked to performance indicators, have a inhibitory effect on green technology innovation. Internal and external institutional factors such as energy conservation measures, the “three wastes” management system, and environmental recognition play the regulatory role in the relationship between incentive contracts and green technology innovation.

Those findings validate and expand the efficient contracting hypothesis and the rent extraction hypothesis from the perspective of green technology innovation and provide useful implications for the design of green governance systems in manufacturing enterprises.

Limited geometric accuracy is one of the major challenges that hinder the wider application of additive manufacturing (AM). This paper aims to predict in-plane shape deviation for online inspection and compensation to prevent error accumulation and improve shape fidelity in AM.

A sequence-to-sequence model with an attention mechanism (Seq2Seq+Attention) is proposed and implemented to predict subsequent layers or the occluded toolpath deviations after the multiresolution alignment. A shape compensation plan can be performed for the large deviation predicted.

The proposed Seq2Seq+Attention model is able to provide consistent prediction accuracy. The compensation plan proposed based on the predicted deviation can significantly improve the printing fidelity for those layers detected with large deviations.

Based on the experiments conducted on the knee joint samples, the proposed method outperforms the other three machine learning methods for both subsequent layer and occluded toolpath deviation prediction.

This work fills a research gap for predicting in-plane deviation not only for subsequent layers but also for occluded paths due to the missing scanning measurements. It is also combined with the multiresolution alignment and change point detection to determine the necessity of a compensation plan with updated G-code.

Today's marketing is dominated by decision-making based on artificial intelligence and machine learning. This study focuses on one semi- and unsupervised machine learning technique, generative adversarial networks (GANs). GANs are a type of deep learning architecture capable of generating new data similar to the training data that were used to train it, and thus, it is designed to learn a generative model that can produce new samples. GANs have been used in multiple marketing areas, especially in creating images and video and providing customized consumer contents. Through providing a holistic picture of GANs, including its advantage, disadvantage, ethical considerations, and its current application, the study attempts to provide business some strategical orientations, including formulating strong marketing positioning, creating consumer lifetime values, and delivering desired marketing tactics in product, promotion, pricing, and distribution channel. Through using GANs, marketers will create unique experiences for consumers, build strategic focus, and gain competitive advantages. This study is an original endeavor in discussing GANs in marketing, offering fresh insights in this research topic.

Corporate social responsibility (CSR) and innovation are the two main approaches firms utilize to promote sustainable development. However, as yet, scholars have reached no consensus regarding their precise impact on construction firm performance (CFP), hindering efforts to implement effective sustainable development strategies that improve CFP. In view that a simple linear relationship may not be sufficient to capture their precise pattern, this study aims to unveil the nonlinear impact of CSR and innovation on CFP, especially when construction firms take up a distinct competitive position.

This study first proposed four hypotheses to establish a new theoretical model by incorporating CSR, innovation, CFP and construction firms' competitive position (CFCP). Then the model was tested by using 292 annual observations collected from 75 construction firms in China. A multiple regression model analysis was carried out to analyze the survey data and validate the hypotheses.

The results reveal that both CSR and innovation have a U-shaped impact on the price-to-book ratio of a construction firm, a specific CFP measure. CFCP negatively moderates the U-shaped relationship between CSR and CFP, but positively moderates the U-shaped relationship between innovation and CFP.

This study goes beyond a simple linear view, instead of unveiling the nonlinear U-shaped effects of CSR and innovation on CFP that deepen the understanding of their complex relationships in the construction industry and makes construction firms aware that CSR and innovation can only improve performance if they reach a certain level. The moderating role of CFCP provides important implications for construction firms seeking to adopt appropriate competitive strategies related to social responsibility and innovation that both promote CFP and achieve sustainable development.

During the construction process of the China Railway Track System (CRTS) I type filling layer, the nonwoven fabric bags have been used as grouting templates for cement asphalt (CA) emulsified mortar. The porous structure of nonwoven fabrics endowed the templates with breathability and water permeability. The standard requires that the volume expansion rate of CA mortar must be controlled within 1%–3%, which can generate expansion pressure to ensure that the cavities under track slabs are filled fully. However, the expansion pressure caused some of the water to seep out from the periphery of the filling bag, and it would affect the actual mix proportion of CA mortar. The differences in physical and mechanical properties between the CA mortar under track slabs and the CA mortar formed in the laboratory were studied in this paper. The relevant results could provide important methods for the research of filling layer materials for CRTS I type and other types of ballastless tracks in China.

During the inspection of filling layer, the samples of CA mortar from different working conditions and raw materials were taken by uncovering the track slabs and drilling cores. The physical and mechanical properties of CA mortar under the filling layer of the slab were systematically analyzed by testing the electrical flux, compressive strength and density of mortar in different parts of the filling layer.

In this paper, the electric flux, the physical properties and mechanical properties of different parts of CA mortar under the track slab were investigated. The results showed that the density, electric flux and compressive strength of CA mortar were affected by the composition of raw materials for dry powders and different parts of the filling layer. In addition, the electrical flux of CA mortar gradually decreased within 90 days’ age. The electrical flux of samples with the thickness of 54 mm was lower than 500 C. Therefore, the impermeability and durability of CA mortar could be improved by increasing the thickness of filling layer. Besides, the results showed that the compressive strength of CA mortar increased, while the density and electric flux decreased gradually, with the prolongation of hardening time.

During 90 days' age, the electrical flux of the CA mortar gradually decreased with the increase of specimen thickness and the electrical flux of the specimens with the thickness of 54 mm was lower than 500 C. The impermeability and durability of the CA mortar could be improved by increasing the thickness of filling layer. The proposed method can provide reference for the further development and improvement of CRTS I and CRTS II type ballastless track in China.

Considering rapid digitalization development, this study examines the impacts of digital technology innovation on social responsibility in platform enterprises.

The study applies the event study method and cross-sectional regression analysis, taking 168 digital technology innovations for social responsibility issued by 88 listed platform enterprises from 2011 to 2022 to study the impact of digital technology innovations for social responsibility announcements of different announcement content and platform attributes on the stock market value of platform enterprises.

The results show that, first, the positive stock market reaction is produced on the same day as the digital technology innovation announcement. Second, the announcement of the platform’s public social responsibility and the announcement of co-innovation and radical innovation bring more positive stock market reactions. In addition, the announcements mentioned above issued by trading platforms bring more positive stock market reactions. Finally, the social responsibility attribution characteristics of the announcement did not have a significant differentiated impact on the stock market reaction.

Most scholars have studied digital technology innovation for social responsibility through modeling rather than second-hand data to empirically examine. This study uses second-hand data with the instrumental stakeholder theory to provide a new research perspective on platform social responsibility. In addition, in order to explore the different impacts of digital technology innovation on social responsibility, this study has classified digital technology innovation for social responsibility according to its social responsibility and digital technology innovation characteristics.

Although the prior literature has identified the relevance of dealer participation for multinational enterprises (MNEs), it is unclear whether such participation could also be an important means for local dealers to learn from MNEs. By adopting local firms’ viewpoint, our study draws on organizational learning theory to examine how local dealers benefit from their participation with foreign suppliers in Africa.

The empirical setting is a combinative dataset of secondary data and primary survey of 164 small- and medium-sized local dealers with nine subsidiaries of a Chinese motorcycle company in six countries of Sub-Saharan Africa.

This research shows that dealer participation is positively associated with dealer performance, and this positive effect is stronger when local dealers operate in regions with low government corruption and high government support. However, the positive relationship is weaker when local dealers use the local tongue extensively but becomes stronger when their foreign suppliers have a high dealer coverage.

By taking a local-participant perspective, our study extends the participation literature to show how firms from a resource-constrained region may benefit from their proactive participation with foreign counterparts. Additionally, we identify the boundary conditions of institutional factors and strategic choices of local dealers and foreign suppliers, providing a nuanced understanding of firm behaviors in complex and uncertain markets.

This paper aims to develop a novel grey Bernoulli model with memory characteristics, which is designed to dynamically choose the optimal memory kernel function and the length of memory dependence period, ultimately enhancing the model's predictive accuracy.

This paper enhances the traditional grey Bernoulli model by introducing memory-dependent derivatives, resulting in a novel memory-dependent derivative grey model. Additionally, fractional-order accumulation is employed for preprocessing the original data. The length of the memory dependence period for memory-dependent derivatives is determined through grey correlation analysis. Furthermore, the whale optimization algorithm is utilized to optimize the cumulative order, power index and memory kernel function index of the model, enabling adaptability to diverse scenarios.

The selection of appropriate memory kernel functions and memory dependency lengths will improve model prediction performance. The model can adaptively select the memory kernel function and memory dependence length, and the performance of the model is better than other comparison models.

The model presented in this article has some limitations. The grey model is itself suitable for small sample data, and memory-dependent derivatives mainly consider the memory effect on a fixed length. Therefore, this model is mainly applicable to data prediction with short-term memory effect and has certain limitations on time series of long-term memory.

In practical systems, memory effects typically exhibit a decaying pattern, which is effectively characterized by the memory kernel function. The model in this study skillfully determines the appropriate kernel functions and memory dependency lengths to capture these memory effects, enhancing its alignment with real-world scenarios.

Based on the memory-dependent derivative method, a memory-dependent derivative grey Bernoulli model that more accurately reflects the actual memory effect is constructed and applied to power generation forecasting in China, South Korea and India.