Search results

The purpose of this paper is to improve the precision of gangue detection. In the real production environment, some gangue features are not obvious, and it is difficult to distinguish between coal and gangue. The color of the conveyor belt is similar to the gangue, the background noise also brings challenge to gangue detection. To address the above problems, we propose a feature aggregation method based on optical flow (FAOF).

An FAOF is proposed. First, to enhance the feature representation of the current frame, FAOF applies the timing information of video stream, propagates the feature information of the past few frames to the current frame by optical flow. Second, the coordinate attention (CA) module is adopted to suppress the noise impact brought by the background of convey belt. Third, the Mish activation function is used to replace rectified linear unit to improve the generalization capability of our model.

The experimental results show that the gangue detection model proposed in this paper improve 4.3 average precision compared to baseline. This model can effectively improve the accuracy of gangue detection in real production environment.

The key contributions are as follows: this study proposes an FAOF; this study adds CA module and Mish to reduce noise from the background of the conveyor belt; and this study also constructs a large gangue data set.

Assessing the failure probability of engineering structures is still a challenging task in the presence of various uncertainties due to the involvement of expensive-to-evaluate computational models. The traditional simulation-based approaches require tremendous computational effort, especially when the failure probability is small. Thus, the use of more efficient surrogate modeling techniques to emulate the true performance function has gained increasingly more attention and application in recent years. In this paper, an active learning method based on a Kriging model is proposed to estimate the failure probability with high efficiency and accuracy.

To effectively identify informative samples for the enrichment of the design of experiments, a set of new learning functions is proposed. These learning functions are successfully incorporated into a sampling scheme, where the candidate samples for the enrichment are uniformly distributed in the n-dimensional hypersphere with an iteratively updated radius. To further improve the computational efficiency, a parallelization strategy that enables the proposed algorithm to select multiple sample points in each iteration is presented by introducing the K-means clustering algorithm. Hence, the proposed method is referred to as the adaptive Kriging method based on K-means clustering and sampling in n-Ball (AK-KBⁿ).

The performance of AK-KBⁿ is evaluated through several numerical examples. According to the generated results, all the proposed learning functions are capable of guiding the search toward sample points close to the LSS in the critical region and result in a converged Kriging model that perfectly matches the true one in the regions of interest. The AK-KBⁿ method is demonstrated to be well suited for structural reliability analysis and a very good performance is observed in the investigated examples.

In this study, the statistical information of Kriging prediction, the relative contribution of the sample points to the failure probability and the distances between the candidate samples and the existing ones are all integrated into the proposed learning functions, which enables effective selection of informative samples for updating the Kriging model. Moreover, the number of required iterations is reduced by introducing the parallel computing strategy, which can dramatically alleviate the computation cost when time demanding numerical models are involved in the analysis.

This paper aims to deal with the coordination problem of the supply chain through cost sharing of corporate social responsibility (CSR) and government subsidy.

With respect to the coordination problem of the supply chain with CSR, this paper constructs a three-stage game model consisting of a dominant retailer, n suppliers and government. From the perspective of cost sharing and government subsidies, this paper discussed the decentralized and centralized decision-making, respectively. On this basis, this paper designed a coordination mechanism considering both cost sharing and government subsidies and explore the impact of cost sharing rate and government subsidy rate on CSR efforts, members’ profits and social welfare.

CSR can improve the profits of supply chain members and the overall performance of the supply chain. Then the profits of supply chain nodal enterprises will be affected by the fulfillment level of CSR of their partners. Furthermore, excessive CSR will erode the supply chain profits and cause resource waste. High CSR costs often make retailers low CSR effort level, while a high CSR cost sharing rate can reduce the profits of suppliers and the supply chain. In addition, excessive government subsidies will lead to the decline of social welfare. Excessive government subsidies will cause the dependence of enterprises and affect their operating efficiency.

The proposed coordination mechanism can effectively do with the coordination problem of the supply chain.

The proposed coordination mechanism considering cost sharing and government subsidies simultaneously can effectively deal with conflict problems and guarantee the supply chain members and the supply chain to maximize their profits and social welfare.

Research on entrepreneurship toward poverty reduction has outlined how micro-level characteristics of entrepreneurs capture entrepreneurial opportunities in settings of poverty; however, little is known about the influence of previous military experience in this context. This paper investigates how previous military experience influences poverty-reduction entrepreneurship.

This study uses data from two main sources. First, individual-level and firm-level information come from a nationwide survey of founders of private enterprises. Second, province-level information is taken from the Marketization Index and the China Statistics Yearbook. An analysis of the Logit moderation model renders strong support for our conjectures.

Via novel integration of imprinting theory and research on previous military experience, we propose that entrepreneurs with previous military experience have a strong sense of self-sacrifice, and as a result, are better able to participate in poverty-reduction entrepreneurship. In addition, we build on the resource availability and stakeholder expectations arguments and predict that the main effect of previous military experience on poverty-reduction entrepreneurship will be strengthened by reduced corporate philanthropy and increased government intervention.

Our study adds to the extant literature in the following ways. First, it enriches the literature on entrepreneurship toward poverty reduction. Second, it contributes to imprinting theory in the entrepreneurial field. Third, it adds knowledge to the social entrepreneurship literature.

This paper aims to deal with the trade-off of the stability and the accuracy in learning human control strategy from demonstrations. With the stability conditions and the estimated stability region, this paper aims to conveniently get rid of the unstable controller or controller with relatively small stability region. With this evaluation, the learning human strategy controller becomes much more robust to perturbations.

In this paper, the criterion to verify the stability and a method to estimate the domain of attraction are provided for the learning controllers trained with support vector machines (SVMs). Conditions are formulated based on the discrete-time system Lyapunov theory to ensure that a closed-form of the learning control system is strongly stable under perturbations (SSUP). Then a Chebychev point based approach is proposed to estimate its domain of attraction.

Some of such learning controllers have been implemented in the vertical balance control of a dynamically stable, statically unstable wheel mobile robot.

The online direct selling mode has been widely accepted by enterprises in the O2O era. However, the dual-channel (online/offline, forward/backward) operations of the closed-loop supply chain (CLSC) changed the relationship between manufacturers and retailers, thus resulting in channel conflict. The purpose of this paper is to take a dual-channel operations of CLSC as the research target, where a manufacturer sells a single product through a direct e-channel as well as a conventional retail channel; the retailer are responsible for collecting used products in the reverse supply chain and the manufacturer are responsible for remanufacturing.

The authors build a benchmark model of dual-channel price and service competition and take the return rate, which is considered to be related to the service level of the retailer, as the function of the service level to extend the model in the reverse SC. The authors then analyze the optimal pricing and service decision under centralization and decentralization, respectively. Finally, with the revenue-sharing factor, wholesale price and recycling price transfer payment coefficient as contract parameters, the paper also designs a revenue-sharing contract led by the manufacturer and explores in what situation the contract could realize the Pareto optimization of all players.

In the baseline model, the results show that optimal price and service level correlate positively in centralization; however, the relation relies on consumers’ price sensitivity in decentralization. In the extension model, the relationship between price and service level also relies on the relative value of increased service cost and remanufacturing saved cost. When the return rate correlates with the service level, a recycling transfer payment can elevate the service level and thus raise the return rate. Through analyzing the parameters in revenue-sharing contract, a point can be reached where lowering the wholesale price and raising the transfer payment coefficient will promote retailers to share revenue.

Many enterprises establish the dual-channel distribution system both online and offline, which need to understand how to resolve their channel conflict. The conflict is especially strong in CLSC with remanufacturing. The result helps the node enterprises realize the coordination of the dual-channel CLSC.

It takes into account the fact that there are two complementary relationships, such as online selling and offline delivery; used product recycling and remanufacturing. The authors optimize the strategy of product pricing and service level in order to solve channel conflict and double marginalization in the closed-loop dual-channel distribution network.

The purpose of this paper is to improve the corrosion resistance of the 6061-Al alloy as the battery pack material for electric vehicles, and the nano-SiC/MAO composite coating was prepared.

The corrosion resistance of coatings was evaluated by the global electrochemical test, and the local electrochemical impedance spectroscopy (LEIS) was used to study the local corrosion mechanism. The laser confocal microscope, scanning electron microscope and X-ray diffractometer (XRD) were used to characterise coatings.

Results showed that the impedance of nano-SiC/MAO coating was 1–2 times higher than MAO coating, and the main corrosion product was Al(OH)₃. LEIS results showed that the impedance of the nano-SiC/MAO coating was two times higher than the MAO coating. The defective SiC/Micro-arc oxidation coating still had high corrosion resistance compared to the MAO coating.

The physical model of the local corrosion mechanism for SiC/MAO composite coating in “cavity-fracture collapse” mode was proposed.