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.

This study aims to explore the success factors of tourism performing arts (TPA) programs by analyzing a large data set of online reviews.

A total of 195,230 reviews from Ctrip.com were collected and preprocessed. A deep learning method was leveraged to estimate the similarity between words. Then, regression analysis was conducted to determine success factors.

This study extracted four positive and two negative factors affecting tourist satisfaction with tourism performance arts. The results demonstrate that the tourists paid the most attention to the traditional Chinese cultural aspects, audiovisual effects and the actors’ performing enthusiasm.

Despite this study’s large data set, the focused was only on Chinese reviews. It would be useful and interesting to compare the success factors of tourism performance arts programs offered in different countries.

The study findings can contribute to the development of TPA programs to attract tourists to travel destinations.

This study demonstrates that analyzing online reviews of TPA through text mining technology is an effective method of understanding tourist satisfaction.

在线点评分析探析旅游演艺成功因素

本研究旨在通过分析大型在线评论数据集来探索旅游表演艺术项目的成功因素。

共收集和预处理来自携程网的 195,230 条评论。利用深度学习方法来估计单词之间的相似性。然后, 进行回归分析以确定成功因素。

本研究提取了影响游客对旅游表演艺术满意度的四个积极因素和两个消极因素。结果表明, 游客最关注中国传统文化方面、视听效果和演员的表演热情。

尽管我们的数据集很大, 但它只关注中文评论。比较不同国家提供的旅游表演艺术项目的成功因素将是有用和有趣的未来研究方向。

研究结果有助于发展旅游表演艺术项目, 以吸引游客前往旅游目的地。

研究表明, 通过文本挖掘技术分析旅游表演艺术的在线评论是了解游客满意度的有效方法。

Because of indeterminateness of the environment and delay of the communication, deep space spacecraft is required to be autonomous. Planning technology is studied in order to realize the spacecraft autonomy. First, a multi‐agent planning system (MAPS) based on temporal constraint satisfaction is proposed for concurrency and distribution of spacecraft system. Second, timeline concept is used to describe simultaneous activity, continue time, resource and temporal constraints. Third, for every planning agent in the MAPS, its layered architecture is designed and planning algorithm based on the temporal constraint satisfaction is given in detail. Finally, taking some key subsystems of deep space explorer as an example, the prototype system of MAPS is implemented. The results show that with the communication and cooperation of the planning agents, the MAPS is able to produce complete plan for explorer mission quickly under the complex constraints of time and resource.

This paper aims to provide a well-behaved nonlinear scheme and accelerating iteration for the nonlinear convection diffusion equation with fundamental properties illustrated.

A nonlinear finite difference scheme is studied with fully implicit (FI) discretization used to acquire accurate simulation. A Picard–Newton (PN) iteration with a quadratic convergent ratio is designed to realize fast solution. Theoretical analysis is performed using the discrete function analysis technique. By adopting a novel induction hypothesis reasoning technique, the L^∞ (H¹) convergence of the scheme is proved despite the difficulty because of the combination of conservative diffusion and convection operator. Other properties are established consequently. Furthermore, the algorithm is extended from first-order temporal accuracy to second-order temporal accuracy.

Theoretical analysis shows that each of the two FI schemes is stable, its solution exists uniquely and has second-order spatial and first/second-order temporal accuracy. The corresponding PN iteration has the same order of accuracy and quadratic convergent speed. Numerical tests verify the conclusions and demonstrate the high accuracy and efficiency of the algorithms. Remarkable acceleration is gained.

The numerical method provides theoretical and technical support to accelerate resolving convection diffusion, non-equilibrium radiation diffusion and radiation transport problems.

The FI schemes and iterations for the convection diffusion problem are proposed with their properties rigorously analyzed. The induction hypothesis reasoning method here differs with those for linearization schemes and is applicable to other nonlinear problems.

To meet the high stiffness requirement of bearings used in high-precision spindles, this paper aims to propose a novel kind of bearing composited by hydrostatic cavities and tilting pads with preload.

Cavities are cut on the oil seal surface of a hybrid bearing, in which the tilting pads are set up. The load of the bearing is carried by the hydrostatic cavities and tilting pads. The structural features of this compound bearing and the controlling variables of the main stiffness coefficient are presented. Two basic design principles are proposed on the basis of equal machining clearance (EMC) and equal installation clearance (EIC).

The theoretical analysis indicates that the stiffness of compound bearings under the EMC condition increases to infinity monotonously when the preload coefficient of the tilting pad tends to 1, while the stiffness under the EIC condition has a peak value. Therefore, a synthetic design principle is proposed by synthetically using the above-mentioned two principles. The applicable range of the three principles is discussed through an example.

The study about technological combination of hydrostatic cavity and tilting pad in this paper can provide suggestions for the design of a high-stiffness bearing in a precision spindle.

The purpose of this paper is to introduce a low power digital‐to‐analog converter (DAC) by using a sequential triggering technique in cascaded current source.

The block of current cell consists of current switch and source. A sequential switching on process is implemented with the current triggering technique in source. An experiment of 12‐b 150‐MS/s DAC has been integrated in a single‐poly four‐metal 0.35 μm CMOS process.

Compared with conventional cell array in 12‐b 150‐MS/s DAC, the proposed cell array shows that more than 30 percent of power consumption is reduced in full digital bit operation with allowable linearity error of 0.4 LSB.

This paper presents a new operation method of cell array in a current‐steering digital‐to‐analog converter (DAC) to reduce the power consumption significantly.

This paper aims to investigate, a new optimization algorithm for complex orbit transfer missions with low‐thrust propulsion system, which minimizes the drawbacks of traditional optimization methods, such as bad convergence, difficulty of initial guesses and local optimality.

First, the trajectory optimization problem comes down to a nonlinear constraint parameter optimization by using the concept of traditional hybrid method. Then, one utilizes genetic algorithm (GA) to solve this parameter optimization problem after treating the constraints with the simulated annealing (SA) and random penalty function. Finally, one makes use of localized optimization to improve the precision of the final solutions.

This algorithm not only keeps the advantages of traditional hybrid method such as high precision and smooth solutions, but also inherits the merits of GA which could avoid initial guess work and obtain a globally optimal solution.

Further, research is required to reduce the computational complexity when the transfer trajectory is very complex and/or has many adjustable variables.

By using this method, the globally optimal solutions of some complex missions, which could not be obtained by traditional method, could be found.

This method combines the GA with traditional hybrid method, and utilizes SA and random penalty functions to treat with constraints, and then gives out a super convergence way to find the globally optimal low‐thrust transfer orbit.

The purpose of this paper is to describe the application of low‐glitch current cell in a digital to analog converter (DAC) to reduce the clock‐feedthrough effect and achieve a low power consumption.

A low‐glitch current switch cell is applied in a ten‐bit two‐stage DAC which is composed of a unary cell matrix for six most significant bits and a binary weighted array for four least significant bits (LSBs). The current cell is composed of four transistors to neutralize the clock‐feedthrough effect and it enables DAC to operate in good linearity and low power consumption. The prototype DAC is being implemented in a 0.35μm complementary metal‐oxide semiconductor process. The reduction in glitch energy and power consumption has been realized by preliminary experiment and simulation.

Compared to conventional current cell, more than 15 per cent reduction of glitch energy has been obtained in this work. The DAC is estimated that differential nonlinearity is within 0.1 LSB and the maximum power consumption is 68 mW at the sampling frequency of 100 MHz.

Comparison with other conventional work indicates that the current cell proposed in this paper shows much better performance in terms of switching spike and glitch, which may come from the extra dummy transistor in cell and reduce the clock‐feedthrough effect.

The purpose of this paper is to present the design and optimization of a comparator with two transistors.

The effect of back‐gate bias in MOSFET is analyzed and applied to a comparator circuit in a flash‐type A/D converter (ADC). The 4‐bit flash ADC is simply structured by change of comparator block based on CMOS latch with pMOSFET switch. The back‐gate bias on MOSFET changes the threshold voltage and provides for a CMOS inverter to shift the voltage transfer characteristics. In the new type comparator, the variation of turn‐on voltage is controlled within 0.1 V in 4‐bit ADC. The fabrication is done in a 0.35 μm single‐poly four‐metal process.

Layout simulation shows that INL is within 0.3 LSB and SNDR is 25.4 dB at input frequency of 20 KHz and sampling rate of 4 MS/s. The 0.26 × 0.43 mm 2 ADC dissipates 1.2 mW at supply voltage of 3.3 V.

A comparator which uses the effect of the back‐gate bias on MOSFET is applied to a flash ADC. The paper is of value in showing how the circuit of this comparator is quite simple compared with a conventional comparator based on a CMOS latch, which is adaptable for a low‐power analog circuit in future. The experimental output of the 4‐bit flash ADC shows a good agreement with a simulation. Power consumption 1.2 mW, INL 0.2 LSB, and SNDR 25 dB are obtained in the simulation study.