Search results

To realize classification of different pavements, a road roughness acquisition system design and an improved restricted Boltzmann machine deep neural network algorithm based on Adaboost Backward Propagation algorithm for road roughness detection is presented in this paper. The developed measurement system, including hardware designs and algorithm for software, constitutes an independent system which is low-cost, convenient for installation and small.

The inputs of restricted Boltzmann machine deep neural network are the vehicle vertical acceleration power spectrum and the pitch acceleration power spectrum, which is calculated using ADAMS finite element software. Adaboost Backward Propagation algorithm is used in each restricted Boltzmann machine deep neural network classification model for fine-tuning given its performance of global searching. The algorithm is first applied to road spectrum detection and experiments indicate that the algorithm is suitable for detecting pavement roughness.

The detection rate of RBM deep neural network algorithm based on Adaboost Backward Propagation is up to 96 per cent, and the false positive rate is below 3.34 per cent. These indices are both better than the other supervised algorithms, which also performs better in extracting the intrinsic characteristics of data, and therefore improves the classification accuracy and classification quality. Additionally, the classification performance is optimized. The experimental results show that the algorithm can improve performance of restricted Boltzmann machine deep neural networks. The system can be used for detecting pavement roughness.

This paper presents an improved restricted Boltzmann machine deep neural network algorithm based on Adaboost Backward Propagation for identifying the road roughness. Through the restricted Boltzmann machine, it completes pre-training and initializing sample weights. The entire neural network is fine-tuned through the Adaboost Backward Propagation algorithm, verifying the validity of the algorithm on the MNIST data set. A quarter vehicle model is used as the foundation, and the vertical acceleration spectrum of the vehicle center of mass and pitch acceleration spectrum were obtained by simulation in ADAMS as the input samples. The experimental results show that the improved algorithm has better optimization ability, improves the detection rate and can detect the road roughness more effectively.

Internet + and Electronic Business in China is a comprehensive resource that provides insight and analysis into E-commerce in China and how it has revolutionized and continues to revolutionize business and society. Split into four distinct sections, the book first lays out the theoretical foundations and fundamental concepts of E-Business before moving on to look at internet+ innovation models and their applications in different industries such as agriculture, finance and commerce. The book then provides a comprehensive analysis of E-business platforms and their applications in China before finishing with four comprehensive case studies of major E-business projects, providing readers with successful examples of implementing E-Business entrepreneurship projects.

Internet + and Electronic Business in China is a comprehensive resource that provides insights and analysis into how E-commerce has revolutionized and continues to revolutionize business and society in China.

With respect to multiple attribute group decision-making (MAGDM) in which the assessment values of alternatives are denoted by normal discrete fuzzy variables (NDFVs) and the weight information of attributes is incompletely known, this paper aims to develop a novel fuzzy stochastic MAGDM method based on credibility theory and fuzzy stochastic dominance, and then applies the proposed method for selecting the most desirable investment alternative under uncertain environment.

First, by aggregating the membership degrees of an alternative to a scale provided by all decision-makers into a triangular fuzzy number, the credibility degree and expect the value of a triangular fuzzy number are calculated to construct the group fuzzy stochastic decision matrix. Second, based on determining the credibility distribution functions of NDFVs, the fuzzy stochastic dominance relations between alternatives on each attribute are obtained and the fuzzy stochastic dominance degree matrices are constructed by calculating the dominance degrees that one alternative dominates another on each attribute. Subsequently, calculating the overall fuzzy stochastic dominance degrees of an alternative on each attribute, a single objective non-linear optimization model is established to determine the weights of attributes by maximizing the relative closeness coefficients of all alternatives to positive ideal solution. If the information about attribute weights is completely unknown, the idea of maximizing deviation is used to determine the weights of attributes. Finally, the ranking order of alternatives is determined according to the descending order of corresponding relative closeness coefficients and the best alternative is determined.

This paper proposes a novel fuzzy stochastic MAGDM method based on credibility theory and fuzzy stochastic dominance, and a case study of investment alternative selection problem is provided to illustrate the applicability and sensitivity of the proposed method and its effectiveness is demonstrated by comparison analysis with the proposed method with the existing fuzzy stochastic MAGDM method. The result shows that the proposed method is useful to solve the MAGDM problems in which the assessment values of alternatives are denoted by NDFVs and the weight information of attributes is incompletely known.

The contributions of this paper are that to describe the dominance relations between fuzzy variables reasonably and quantitatively, the fuzzy stochastic dominance relations between any two fuzzy variables are redefined and the concept of fuzzy stochastic dominance degree is proposed to measure the dominance degree that one fuzzy variable dominate another; Based on credibility theory and fuzzy stochastic dominance, a novel fuzzy stochastic MAGDM method is proposed to solve MAGDM problems in which the assessment values of alternatives are denoted by NDFVs and the weight information of attributes is incompletely known. The proposed method has a clear logic, which not only can enrich and develop the theories and methods of MAGDM but also provides decision-makers a novel method for solving fuzzy stochastic MAGDM problems.

The purpose of this paper is to extend game analysis to explore decision-making mechanisms for promoting a specific type of products, low energy consumption for individual one while the total energy consumption is huge due to the high quantity of sales, that is, low for individual and high for total (LIHT) in terms of energy consumption.

Game models are developed to compare decisions of optimal prices for newly developed and environmentally friendly (NDEF) and regular products as well as associated sales quantity, profits, carbon emissions under different governmental policies, along with a case of low energy-intensive broadband terminal products in the Chinese telecommunication industry under the carbon tax and subsidy policies.

For both NDEF and regular products, optimal prices decrease under the subsidy policy while both increase under the tax policy. Manufacturers’ decision of optimal prices is highly relevant with unit carbon tax/subsidy and the consumers’ preference. Both the tax and subsidy policies can improve consumption of NDEF products while the subsidy policy can be more effective at the current initial stage.

This paper provides decision support for manufacturers to promote sustainable consumption of LIHT products. Research ideas on models development and solutions for optimal prices can be applied to other LIHT products.

The results provide insights for governments on how to effectively evaluate and motivate sustainable consumption for LIHT products.

This paper first explores how to motivate sustainable consumption of LIHT products by developing models, examining effectiveness of potential governmental policies as well as associated carbon emissions.

China is the world's largest consumer of pesticides. To increase the use efficiency and achieve more sustainable and environmentally friendly use of pesticides in China, it is crucial to understand why Chinese farmers use such a large amount of pesticides.

The relationship between farm size and pesticide use was investigated by using national household-level panel data from 1995 to 2016.

Farms that are small and fragmented lead to the use of large amounts of pesticides in China. For a given crop type, three factors contribute to a negative relationship between farm size and pesticide use: the spillover effect from the use of pesticides by other farmers in the same village, the level of mechanization and the management ability of farmers. The first two factors play important roles in the cultivation of grain crops, while the last factor is the main reason why farmers with larger plots of land use fewer pesticides in the cultivation of vegetables. In addition, the effect of agricultural machinery services on reducing the use of pesticides is currently limited, and the service system in China is still insufficient, which has been pointed out that it is also due to the prevalence of small and fragmented farms.

The authors investigate and compare the farm size–pesticide use relationship in both grain and cash crop production. Moreover, the authors systematically explore and explain how farm size is related to a reduction in pesticide use in the cultivation of grain crops and cash crops. These results can help to better understand the role of land scale in pesticide use, lay a foundation for the formulation of policies to reduce pesticide use and provide valuable knowledge about pesticide use for other developing countries around the world.

This study aims to develop a comprehensive green supplier governance (GSG) concept and explore whether specific GSG approaches (green supplier assessment, green supplier assistance and green strategic partnership with suppliers (GSPS)) bring environmental and economic performance. Moreover, this study aims to reveal a synergistic effect of three GSG approaches on performance improvement.

Using data collected from 200 Chinese manufacturing firms, regression analysis was employed to reveal the relationship between specific GSG approaches and firm performance. Further, cluster analysis was used to identify groupings of firms regarding implementation levels of three GSG approaches and compare the performance of the firm groups.

Green supplier assessment (GSA) can bring environmental performance, but GSA is not associated with economic performance. Green supplier assistance is positively associated with economic performance, while green supplier assistance cannot improve environmental performance. Only GSPS leads to improvement for both environmental and economic performance. Furthermore, firms with high implementation levels of GSA and GSPS (whether with high or low implementation levels of GSAS) can achieve the best environmental and financial performance.

This study provides implications for firms to more strategically and comprehensively implement GSG approaches, which can be more effective in bringing environmental and economic performance.

The authors' study extends the GSG concept with two approaches by subdividing the collaborative approach into green supplier assistance and GSPS based on the collaboration levels. This study also sheds light on how to improve firm performance by different GSG approaches and reveals a synergistic effect of three GSG approaches on performance.

The purpose of this paper is to propose a seamless autonomous navigation method based on the motion constraint of the mobile robot, which is able to meet the practical need of maintaining the navigation accuracy during global positioning system (GPS) outages.

The seamless method uses the motion constraint of the mobile robot to establish the filter model of the system, in which the virtual observation about the speed is used to overcome the shortage of the navigation accuracy during GPS outages. The corresponding motion constraint model of the mobile robot is established. The proposed seamless navigation scheme includes two parts: the micro inertial navigation system (MINS)/GPS-integrated filter model and the motion constraint filter model. When the satellite signals are good, the system works on the MINS/GPS-integrated mode. If some obstacles block the GPS signals, the motion constraint measurement equation will be effective so as to improve the navigation accuracy of the mobile robot.

Three different vehicle tests of the mobile robot show that the seamless navigation method can overcome the shortage of the navigation accuracy during GPS outages, so as to improve the navigation performance in practical applications.

A seamless navigation system based on the motion constraint of the mobile robot is proposed to overcome the shortage of the navigation accuracy during GPS outages, thus improving the adaptability of the robot navigation.

The diagnosis and prediction methods used for estimating the health conditions of the bearing are of great significance in modern petrochemical industries. This paper aims to discuss the accuracy and stability of improved empirical mode decomposition (EMD) algorithm in bearing fault diagnosis.

This paper adopts the improved adaptive complementary ensemble empirical mode decomposition (ICEEMD) to process the nonlinear and nonstationary signals. Two data sets including a multistage centrifugal fan data set from the laboratory and a motor bearing data set from the Case Western Reserve University are used to perform experiments. Furthermore, the proposed fault diagnosis method, combined with intelligent methods, is evaluated by using two data sets. The proposed method achieved accuracies of 99.62% and 99.17%. Through the experiment of two data, it can be seen that the proposed algorithm has excellent performance in the accuracy and stability of diagnosis.

According to the review papers, as one of the effective decomposition methods to deal with nonlinear nonstationary signals, the method based on EMD has been widely used in bearing fault diagnosis. However, EMD is often used to figure out the nonlinear nonstationarity of fault data, but the traditional EMD is prone to modal confusion, and the white noise in signal reconstruction is difficult to eliminate.

In this paper only the top three optimal intrinsic mode functions (IMFs) are selected, but IMFs with less correlation cannot completely deny their value. Considering the actual working conditions of petrochemical units, the feasibility of this method in compound fault diagnosis needs to be studied.

Different from traditional methods, ICEEMD not only does not need human intervention and setting but also improves the extraction efficiency of feature information. Then, it is combined with a data-driven approach to complete the data preprocessing, and further carries out the fault identification and classification with the optimized convolutional neural network.

Green supply chain management (GSCM) and the circular economy (CE) overlap but also differ. The purpose of this paper is to clarify linkages between these two concepts. It identifies mutual theory applications used to study GSCM and CE.

A systematic literature review is conducted to identify theories from GSCM and CE studies. A critical analysis explores the theories that can provide mutual applications between GSCM and CE fields. Propositions are developed.

In all, 12 theories are applied in both GSCM and CE studies. Several theories are only applied in GSCM studies, but can help to advance CE study. These theories include complexity, transaction cost economics, agency, and information theories. Each of the eight theories only applied to CE can potentially advance GSCM study.

The findings contribute to further theory development for both GSCM and CE study. A methodological review can advance theoretical development and cross-pollination in both fields.

This work is the first study to explicitly explore linkages of GSCM and CE from a theoretical perspective.

The titania (titanium dioxide) is one of the important functional additives in the photosensitive resin and encounters the problem of stabilization in the photosensitive resin for 3D printing. This study aims to achieve enhancement in stabilization by preparation of the polymerizable titania and in situ laser-induced crystallization during 3D printing.

A type of polymerizable titania (AAEM@TiO₂) was designed and prepared from tetrabutyl titanate (TBT) and 2-(acetoacetoxy)ethyl methacrylate (AAEM) via the sol–gel process, which was characterized by Fourier-transform infrared (FTIR) spectra, ultraviolet–visible (UV-Vis) spectra, surface bonding efficiency (SBE) and settling height (H). AAEM acted on both bonding to the titania and polymerization with the monomer in resin for stabilization. The polymerizable titania could be converted to the pigmented titania by means of laser-induced crystallization. The photosensitive resin was then formulated on the basis of optimization and used in a stereolithography apparatus (SLA) for 3D printing.

The stabilization effect of AAEM on TiO₂ was achieved and the mechanism of competition in the light-consuming reactions during photocuring was proposed. The ratio of n_AAEM/n_TBT in AAEM@TiO₂, the concentration of AAEM@TiO₂ and photoinitiator (PI) used in the photosensitive resin were optimized. The anatase crystal form was indicated by X-ray diffraction (XRD) and clustering of nanocrystals was revealed by scanning electron microscopy (SEM) after SLA 3D printing.

This investigation provides a novel method of pigmentation by preparation of the polymerizable titania and in situ laser-induced crystallization for SLA 3D printing.