Search results

The purpose of this paper is to present a weakly supervised learning method to perform health evaluation and predict the remaining useful life (RUL) of rolling bearings.

Based on the principle that bearing health degrades with the increase of service time, a weak label qualitative pairing comparison dataset for bearing health is extracted from the original time series monitoring data of bearing. A bearing health indicator (HI) quantitative evaluation model is obtained by training the delicately designed neural network structure with bearing qualitative comparison data between different health statuses. The remaining useful life is then predicted using the bearing health evaluation model and the degradation tolerance threshold. To validate the feasibility, efficiency and superiority of the proposed method, comparison experiments are designed and carried out on a widely used bearing dataset.

The method achieves the transformation of bearing health from qualitative comparison to quantitative evaluation via a learning algorithm, which is promising in industrial equipment health evaluation and prediction.

The method achieves the transformation of bearing health from qualitative comparison to quantitative evaluation via a learning algorithm, which is promising in industrial equipment health evaluation and prediction.

The purpose of this paper is to propose a new deep learning-based model to carry out better maintenance for naval propulsion system.

This model is constructed by integrating different deep learning algorithms. The basic idea is to change the connection structure of the deep neural network by introducing a residual module, to limit the prediction output to a reasonable range. Then, connect the Deep Residual Network (DRN) with a Generative Adversarial Network (GAN), which helps achieve data expansion during the training process to improve the accuracy of the assessment model.

Study results show that the proposed model achieves a better prediction effect on the dataset. The average performance and accuracy of the proposed model outperform the traditional models and the basic deep learning models tested in the paper.

The proposed model proved to be better performed naval propulsion system maintenance than the traditional models and the basic deep learning models. Therefore, our model may provide better maintenance advice for the naval propulsion system and will lead to a more reliable environment for offshore operations.

Although interorganizational learning has attracted substantial attention, research about its effects on green innovation is still rare. Combining theories of organizational learning and absorptive capacity, this study explores the relationships among interorganizational learning, green knowledge integration capability (GKIC) and green innovation (GI), and analyzes the moderating role of green absorptive capacity (GAC). Based on resource-based and ambidexterity theories, this study focuses on vertical exploitative (VEL) and lateral explorative learning (LEL). This study expands the research of GI by proposing two different interorganizational learning mechanisms and uncovering the intricate relationship between them and GI.

Based on a sample of 203 Chinese manufacturing firms, the authors used a hierarchical regression analysis and bootstrap method to test the theoretical framework and research hypotheses of this paper.

Results show that VEL and LEL have positive effects on GI. GKIC partially mediates the relationship between VEL and GI and completely mediates the relationship between LEL and GI. Moreover, GAC plays a moderating role between LEL and GKIC and moderates the effect of LEL on GI via GKIC, such that the effect is stronger when GAC increases. However, it does not moderate the relationship between VEL and GKIC.

First, founded on resource-based and ambidexterity theories, this study considers two dimensions of interorganizational learning, VEL and LEL. Second, by testing the mediating role of GKIC, the authors provide a theoretical lens to understand the relationship between interorganizational learning and GI. Third, by examining boundary conditions of GAC, the authors enrich organizational learning and absorptive capacity theory in the context of green development.

The rapid advancement of digital transformation requires a shift in firms’ focus from past met needs to both latent future and unmet past needs. However, how boundary-spanning search with future orientation and past orientation affects breakthrough innovation remains unclear. This study thus aims to investigate the relationship between boundary-spanning search and breakthrough innovation from the perspective of search orientation.

In terms of search orientation, this study divides boundary-spanning search into forward-looking search and backward-looking search. Drawing on resource-based view, this study develops a theoretical model in which big data analytics capability moderates the effects of forward-looking and backward-looking searches on breakthrough innovation. Empirical analyses were conducted on data from China’s advanced manufacturing firms. Research model and hypotheses were tested through multiple regression.

The results confirm that forward-looking search has a positive effect on breakthrough innovation, and big data analytics capability strengthens this positive effect. Furthermore, backward-looking search has an inverted U-shaped effect on breakthrough innovation. Interestingly, as big data analytics capability increases, this inverted U-shaped curve flattens and becomes almost linear.

This study uncovers the different effects of boundary-spanning search with different orientations on breakthrough innovation and extends the research on the relationship between boundary-spanning search and breakthrough innovation by incorporating search orientation. Furthermore, by demonstrating the moderating role of big data analytics capability, this study provides a crucial condition under which boundary-spanning search can enhance breakthrough innovation.

The purpose of this paper is to investigate how boundary-spanning search affects sustainable competitive advantage under the conditions that competitors also search and to test the moderating role of knowledge integration capability.

This paper classifies boundary-spanning search into proactive search and responsive search by considering competition and develops a theoretical model in which knowledge integration capability moderates the effects of proactive and responsive searches on sustainable competitive advantage. Empirical analyses were conducted on the data of 245 Chinese advanced manufacturing firms.

The results show that proactive and responsive searches have inverted U-shaped relationships with sustainable competitive advantage. Moreover, the relationships between proactive and responsive searches and sustainable competitive advantage are moderated by knowledge integration capability. Specifically, as knowledge integration capability increases, the inverted U-shaped relationship between proactive search and sustainable competitive advantage becomes flatter, whereas the inverted U-shaped relationship between responsive search and sustainable competitive advantage becomes almost linear.

This paper enriches the research of boundary-spanning search by considering competition and uncovers how boundary-spanning search affects sustainable competitive advantage under the conditions that competitors also search. Furthermore, this paper sheds light on that the effects of proactive and responsive searches on sustainable competitive advantage are even more complex than inverted U-shaped patterns and provides a contingent viewpoint to deeply understand the relationship between boundary-spanning search and sustainable competitive advantage.