Search results

Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.

This study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.

The adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.

A roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.

Constant or decreasing returns and increasing returns to scale are two kinds of mechanism in economic growth. The goal of supply-side structural reform is to promote the establishment of the mechanism with increasing returns to scale. The paper aims to discuss this issue.

This paper argues that the overall economic structure of the developing economy has been divided into the sector of constant or decreasing returns to scale and the sector of increasing returns to scale due to the dual economic structure. Among them, the supply-side structural reform is mainly to reduce the sector of decreasing returns to scale and increase the sector of increasing returns to scale. Based on the hypothesis of such two-sector economic structure in the supply side of developing economies and on the industrial data, this paper empirically tests the returns to scale of China’s supply structure. The result suggests that so far the sector of constant or decreasing returns to scale dominates the supply structure of China’s economic growth, which results in the state of decreasing returns to scale in China’s overall economy.

Therefore, to realize the long-term sustained growth and transformation of the development pattern of China’s economy, the authors must carry out the supply-side structural reform, vigorously develop the modern industrial sectors characterized by modern knowledge and technology, and promote the development of an innovation-driven economy.

Besides, the authors must accelerate the transformation from traditional industrial sectors to modern industrial sectors, actively promote China’s industrial structure toward rationalization and high gradation, as well as build a modern industrial system so as to facilitate the formation of the mechanism of increasing returns to scale and accelerate the transformation of the driving force of China’s economic growth.

The purpose of this paper is to provide an overview of the evolution of service supply chain management from a behavioural operations perspective, pointing out future research directions for scholars.

This study searched five databases for relevant literature published between 2009 and 2018, selecting 64 papers for this review. The selected literature was categorised according to two dimensions: a service supply chain link perspective and a behavioural factor perspective. Comparative analysis was used to identify gaps in the literature, and five future research agendas were proposed.

In terms of the perspective of service supply chain link, extant literature primarily focuses on service supply and service co-ordination management, and less on service demand and integration management. In terms of the behavioural factor’s perspective, most focus on classic behaviour factors, with less attention paid to emerging behaviour factors. This paper thus proposes five research agendas: demand-oriented management and integrated supply chain-oriented behavioural research; broadening the understanding of the scope of behavioural operations; integrating the latest backgrounds and trends of service industry into the research; greater attention to behavioural operations in service sub-industries; and multimethod combination is encouraged to be used to dig into the interesting research problems.

This study constitutes the first systematic review of service supply chain research from a behavioural perspective. By categorising the literature into two dimensions, the state of existing research is evaluated with an eye towards future research avenues.

This paper aims to examine the association between green innovation and the cost of equity in China. This study relies on the investors’ base perspective and shareholders’ perceived risk perspective to investigate the relation between green innovation and the cost of equity in China.

The paper uses firm-fixed effect regression for a sample of Chinese public companies for the period 2008–2018.

The authors find a negative relationship between green innovation and the cost of equity capital. This negative association is found to be more pronounced for less financially constrained firms, during periods of high economic policy uncertainty, and for firms with a strong internal control environment. Finally, the paper shows that the negative association became more pronounced after the passage of the Environmental Protection Law of China in 2012. The results remain robust to possible endogeneity concerns.

This study contributes to the green innovation literature by documenting that shareholders favorably view firms implementing green innovation policies. The study also has policy implications for Chinese regulators in improving the green credit policy.

This paper examines the different features of China's economic development in different stages of economic globalization. The study finds that the investment- and export-based growth model drove China's high-speed economic growth between 2000 and 2007, which came into existence around 2000 when China plugged into the global production network.

This paper also finds that China slowed down to the New Normal because of the disruption to the socio-economic underpinnings of this growth model. As China adapts to and steers the New Normal, supply-side structural reforms can channel excess capacity to the construction of underground pipe networks in rural areas of central China and fix capital while advance rural revitalization.

At the same time, enterprises must strive to build a key component development platform for key component innovation and the standard-setting power in global manufacturing.

The establishment of a domestic production network integrating the integrated innovation-driven core enterprises and modular producers at different levels can satisfy the dynamic demand structure of China in which standardized demands and personalized demands coexist.

Forecasts of commodity prices are vital issues to market participants and policy makers. Those of corn are of no exception, considering its strategic importance. In the present study, the authors assess the forecast problem for the weekly wholesale price index of yellow corn in China during January 1, 2010–January 10, 2020 period.

The authors employ the nonlinear auto-regressive neural network as the forecast tool and evaluate forecast performance of different model settings over algorithms, delays, hidden neurons and data splitting ratios in arriving at the final model.

The final model is relatively simple and leads to accurate and stable results. Particularly, it generates relative root mean square errors of 1.05%, 1.08% and 1.03% for training, validation and testing, respectively.

Through the analysis, the study shows usefulness of the neural network technique for commodity price forecasts. The results might serve as technical forecasts on a standalone basis or be combined with other fundamental forecasts for perspectives of price trends and corresponding policy analysis.

This research proposes a framework to conceptualise the potential realm of data regarding shipping connectivity for application of data analytics which can be used to generate deeper insights with respect to the state of such linkages and potential areas for practical application.

The study method involved comprehensive presentation of different perspectives of assessing shipping connectivity and levels of data contained within container shipping services and proposed potential application to analyse profitability, performance, competitiveness, risk and environmental impact.

Advances in capabilities to handle large volumes of data offer scope for an integrated approach which utilises all available data from various stakeholders in analyses of liner shipping connectivity. Research shows how different types of data contained in container shipping services are related and can be organised for application of data analytics.

Research implications are offered to shipping lines, port managers and operators and policymakers.

This research presented a conceptual framework that captures the range of data involved in container shipping services and how data analytics can be practically applied in an integrated manner.

This paper is the first in literature to discuss in detail the different levels of data that reside within shipping services that constitute liner shipping connectivity for application of data analytics.