Search results

The purpose of this study is to analyze the intelligent fault diagnosis method of rolling bearing.

The vibration signal data of rolling bearing has long time series and strong noise interference, which brings great difficulties for the accurate diagnosis of bearing faults. To solve those problems, an intelligent fault diagnosis model based on stacked denoising autoencoder (SDAE) and convolutional neural network (CNN) is proposed in this paper. The SDAE is used to process the time series data with multiple dimensions and noise interference. Then the dimension-reduced samples can be put into CNN model, and the fault classification results can be obtained by convolution and pooling operations of hidden layers in CNN.

The effectiveness of the proposed method is validated through experimental verification and comparative experimental analysis. The results demonstrate that the proposed model can achieve an average classification accuracy of 96.5% under three noise levels, which is 3-13% higher than the traditional models and single deep-learning models.

The combined SDAE–CNN model proposed in this paper can denoise and reduce dimensions of raw vibration signal data, and extract the in-depth features in image samples of rolling bearing. Consequently, the proposed model has more accurate fault diagnosis results for the rolling bearing vibration signal data with long time series and noise interference.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-11-2019-0496/

Shadow banking has been evolving rapidly in China, with banks actively using wealth management products (WMPs) to evade regulatory restrictions. These products are the largest constituent of China's shadow banking sector. A large number of these products are off-balance-sheet and considered a substitute for bank deposits. China's banking sector, especially the small and medium-sized banks (SMBs), uses these products to avoid regulatory restrictions and sustainability risk in the deposit market.

This study empirically examined how banks in China, specifically SMBs, utilize these products on a short and long-run basis to manage and control their deposit levels. This study utilized a quarterly panel dataset from 2010 to 2019 for the top 30 Chinese banks, by first implementing a Panel ARDL-PMG model. For cross-sectional dependence, this study further executed a cross-sectional augmented autoregressive distributive lag model (CS-ARDL).

Under regulations avoidance theory, the findings revealed that WMPs and deposits have a stable long-run substitute relationship. Furthermore, the WMP–Deposit substitute relationship was only significant and consistent for SMBs, but not for large four banks. The findings further revealed that the WMP–Deposit substitute relationship existed, even after the removal of the deposit rate limit imposed by the People's Bank of China (PBOC) to control the deposit rates.

The individual bank-issued WMPs' amount data is not available in any database. Therefore, this study utilized the number of WMPs as a proxy for China's banking sector's exposure to the wealth management business.

This research helps policymakers to understand the Deposit–WMP relationship from the off-balance-sheet perspective. During the various stages of interest rate liberalization, banks were given more control to establish their deposit and loan interest rates. However, the deposit rates are still way below the WMP returns, making WMPs more competitive. This research suggests that policymakers should formulate a more balanced strategy regarding deposit rates and WMPs returns.

This study contributes to the existing literature on China's shadow banking by concentrating on the WMPs. This research represents one of the few studies that analyze regulatory arbitrage in terms of the WMP–Deposit relationship. Moreover, the implementation of CS-ARDL panel data models and multiple data sources makes this study's findings more reliable and significant.

The purpose of this paper is to use the most popular deep learning algorithm to complete the vehicle detection in the urban area of MiniSAR image, and provide reliable means for ground monitoring.

An accurate detector called the rotation region-based convolution neural networks (CNN) with multilayer fusion and multidimensional attention (M2R-Net) is proposed in this paper. Specifically, M2R-Net adopts the multilayer feature fusion strategy to extract feature maps with more extensive information. Next, the authors implement the multidimensional attention network to highlight target areas. Furthermore, a novel balanced sampling strategy for hard and easy positive-negative samples and a global balanced loss function are applied to deal with spatial imbalance and objective imbalance. Finally, rotation anchors are used to predict and calibrate the minimum circumscribed rectangle of vehicles.

By analyzing many groups of experiments, the validity and universality of the proposed model are verified. More importantly, comparisons with SSD, LRTDet, RFCN, DFPN, CMF-RCNN, R3Det, SCRDet demonstrate that M2R-Net has state-of-the-art detection performance.

The progress in the field of MiniSAR application has been slow due to strong speckle noise, phase error, complex environments and a low signal-to-noise ratio. In addition, four kinds of imbalances, i.e. spatial imbalance, scale imbalance, class imbalance and objective imbalance, in object detection based on the CNN greatly inhibit the optimization of detection performance.

This research can not only enrich the means of daily traffic monitoring but also be used for enemy intelligence reconnaissance in wartime.

Wealth Management Products (WMPs) are the largest and most crucial component of China's Shadow banking, which are off the balance sheet and considered as a substitute for deposits. Commercial banks in China are involved in the issuance of WMPs mainly to; evade the regulatory restrictions, move non-performing loans away from the balance sheet, chase the profits and take advantage of yield spread (the difference between WMPs yield and deposit rate).

In this study, the authors investigate what bank related characteristics and needs; influenced and prompted the issuance of WMPs. By using a quarterly panel data from 2010 to 2019, this study performed the fixed effects approach favored by the Hausman specification test, and a feasible generalized least square (FGLS) estimation method is employed to deal with any issues of heteroscedasticity and auto-correlation.

This study found that there is a positive and significant association between the non-performing loan ratio and the issuance of WMPs. Moreover, profitability and spread were found to play an essential role in the issuance of WMPs. The findings of this study suggest that WMPs are issued for multi-purpose, and off the balance sheet status of these products makes them very lucrative for regulated Chinese commercial banks.

Non-guaranteed WMPs are considered as an item of shadow banking in China, as banks do not consolidate this type of WMPs into their balance sheet; due to that reason, there is no individual bank data available for the amount of WMPs. The authors use the number of WMPs issued by banks as a proxy for the bank's exposure to the WMPs business.

From a regulatory perspective, this study helps regulators to understand the risk associated with the issuance of WMPs; by providing empirical evidence that Chinese banks issue WMPs to hide the actual risk of non-performing loans, and this practice could mislead the regulators to evaluate the bank credit risk and loan quality. This study also identifies that Chinese banks issue WMPs for multi-purpose; this can help potential investors to understand the dynamics of WMPs issuance.

This research is innovative in its orientation because it is designed to investigate the less explored wealth management products (WMPs) issued by Chinese banks. This study's content includes not only innovation but also contributes to the existing literature on the shadow banking sector in terms of regulatory arbitrage. Moreover, the inclusion of FGLS estimation models, ten years of quarterly data, and the top 30 Chinese banks (covers 70% of the total Chinese commercial banking system's assets) make this research more comprehensive and significant.

This paper aims to study the application of reinforcement learning (RL) in the control of an output-constrained flapping-wing micro aerial vehicle (FWMAV) with system uncertainty.

A six-degrees-of-freedom hummingbird model is used without consideration of the inertial effects of the wings. A RL algorithm based on actor–critic framework is applied, which consists of an actor network with unknown policy gradient and a critic network with unknown value function. Considering the good performance of neural network (NN) in fitting nonlinearity and its optimum characteristics, an actor–critic NN optimization algorithm is designed, in which the actor and critic NNs are used to generate a policy and approximate the cost functions, respectively. In addition, to ensure the safe and stable flight of the FWMAV, a barrier Lyapunov function is used to make the flight states constrained in predefined regions. Based on the Lyapunov stability theory, the stability of the system is analyzed, and finally, the feasibility of RL in the control of a FWMAV is verified through simulation.

The proposed RL control scheme works well in ensuring the trajectory tracking of the FWMAV in the presence of output constraint and system uncertainty.

A novel RL algorithm based on actor–critic framework is applied to the control of a FWMAV with system uncertainty. For the stable and safe flight of the FWMAV, the output constraint problem is considered and solved by barrier Lyapunov function-based control.

The purpose of this study is to analyze the linear induction motor (LIM) thermal field when the motor passes through the discontinuous area of the secondary plate in rail transit operation.

To study the thermal field when the LIM passes through the discontinuous area of the secondary plate, the two-dimensional (2D) electromagnetic field model of the motor is first established to calculate and analyze the electromagnetic field of the LIM, and then the motor thermal field is calculated according to the calculation results of the motor electromagnetic field. Finally, the heat source (the motor loss) and the heat dissipation coefficient are added to the thermal field calculation model to calculate the motor thermal field.

This study found that the discontinuity of the secondary board would lead to changes in the electromagnetic field of the linear induction motor to change, which would reduce the motor efficiency and increase the loss, resulting in a sudden increase in the temperature field of the motor.

The LIM temperature field calculation when the LIM passes through the discontinuous area of the secondary board could provide an early warning for the potential risks of the LIM in rail transit applications.

The purpose of this paper is to analyse the impact of ownership structure on firm valuation and performance across different geographical regions within mainland China.

The authors classify China in six geographical regions and use cross-sectional data of companies with A-shares listed on domestic stock exchanges in China for the year-end 2015. Using data from CSMAR and Wind database, they use multivariate regression technique and analytically compare the consistency of relationship between operational variables of ownership structure with corporate performance and evaluation.

The authors find that institutional ownership and state ownership negatively affect market valuation throughout various geographical regions of China. Further, in East, Northwest, South Central and Southwestern parts of China, managerial ownership and concentration of shareholding among top ten shareholders positively influence return on equity (ROE). Interestingly, institutional shareholding negatively affects return on assets (ROA), while institutional ownership has a neutral effect on profitability margin in Northeast China. Although in northern part of China, this relationship is slightly positive. In East China region, state ownership and ownership concentration are directly proportional to profitability margin.

As some of the findings exhibit weak state of market efficiency in some regions, the study may also be useful in identifying arbitrage opportunities across different regions. Moreover, this study suggests that regions with the same business environment and conditions anywhere around the globe invite same or similar ownership structure for better firm performance and valuation.

The study provides unique understanding of relationship between ownership structure, market valuation and firm performance in various parts of China and will be an addition to the relevant literature. Given a change in company’s ownership structure and considering its region of incorporation, this study will help investment analysts in assessing performance and market valuation of the firm. It will also assist several classes of investors, financial institutions and international businesses in making their investment decisions.

The purpose of this paper is to present key points relating to the development of micro drill bits with high aspect ratios and to provide a solution for high aspect ratio hole drilling.

Based on the analysis of challenges in high aspect ratio hole drilling, key points for the development of micro drills bit with high aspect ratio are discussed. A design example of a micro drill bit with 0.3 mm diameter and a 7.2 mm flute length is presented. Experiments are conducted to verify the performance of the developed micro drill bit.

Helix angle, web thickness and flute land ratio are three key parameters that significantly influence the behaviour of micro drill bits with high aspect ratios. Large helix angle, web thickness and flute land ratio are beneficial in terms of improving the performance of high aspect ratio micro drill bits. Step drilling is essential to prevent drill breakage and to ensure smooth debris evacuation. Meanwhile, proper steps and drilling parameters are of great importance to complete high aspect ratio hole drilling.

The paper highlights key points relating to the development of micro drill bits with high aspect ratios that can provide a satisfactory solution for high aspect ratio micro drill bit design.

The paper aims to present key points regarding the development of an ultra‐small micro drill bit for packaging substrate hole processing.

Key points for the development of ultra‐small drill bits are presented. These are based on a study of the influential mechanisms of micro drill bit material properties, key parameters and coating techniques on the behaviours of micro drill bit. Experiments were conducted to verify the drilling capability of the developed ultra‐small micro drill bits.

The material properties of micro drill bits are of great importance in ensuring the performance. Helix angle, primary face angle and point angle are three key parameters that significantly influence drill bit behaviour. Computer‐aided engineering analysis, temperature monitoring and video monitoring techniques in high‐speed drilling are useful tools for achieving the optimal design of ultra‐small drill bits. Using coating technology on ultra‐small drill bits can improve their hit limits by nearly four times.

The paper highlights key points to consider when developing ultra‐small micro drill bits. The presented points can provide an overall understanding of the challenges and solutions during ultra‐small micro drill bit design. Additionally, this paper presents a solution for packaging substrate ultra‐small hole processing by mechanical drilling.

The purpose of this paper is to develop, test and argue in support of the parsimonious, yet explanatory, collectivistic religion affiliated trust model in e‐commerce.

This article develops an integrated model by using consumer religio‐centrism and religious commitment to identify the collectivistic religion respondents and its impact on initial trust on web‐site. The sample 81 respondents consist of foreign and Chinese Muslim students from various departments of Chongqing University. The research model was then tested using structural equation modeling (SEM) techniques. The statistical approach incorporates path analysis, factor analysis, and linear regression into a theoretical causal model for analysis of latent constructs and measurable variables.

The main finding of this paper is to show that initial trust in a web‐based retailer is influenced by culture, at least as represented by affiliation to a religion. Within a collectivist culture, identification with the Muslim religion, it has been shown that in‐group trust effects can transfer to the web context. Muslim respondents in this study were found to be more trusting of a Muslim site compared to a neutral site.

To date, this is the first research that has been conducted to analyze trust factor from a religion point of view by using structural equation modeling in entire Islamic e‐commerce research.