A method for rapidly evaluating reliability and predicting remaining useful life using two-dimensional convolutional neural network with signal conversion

Qibin Wang,Bo Zhao,Hongbo Ma,Jiantao Chang,Gang Mao 대한기계학회 2019 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.33 No.6

Real-time monitoring and rapid evaluation of bearing operating conditions, especially for the reliability evaluation and remaining useful life (RUL) prediction, are major challenges in the rotating machinery field. A two-dimensional (2-D) deep convolution neural network (CNN) is proposed for rapidly evaluating reliability and predicting RUL, in which a signal conversion method is proposed for converting the one-dimensional signal into the 2-D image to satisfy the input requirements of the 2-D CNN. Different activation functions are employed to implement the conversion of the input data to the output data for each layer of the network, and dropout is only adopted in the hidden layer to change the network structure to prevent overfitting. The maximum correlation entropy with regular terms is employed as the loss function of the model to obtain better training performance compared with the mean square error (MSE). Then, the rolling bearing degradation vibration data is applied to the proposed model to verify the accuracy and rapidity. The results show that the proposed method has good accuracy and fast calculation ability in bearing reliability evaluation and RUL prediction, especially, its time consumption is shorter than that by other deep learning networks.

Effects of different coupling models of a helical gear system on vibration characteristics

Qibin Wang,Zhanwei Li,Hui Ma,Bang-chun Wen 대한기계학회 2017 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.31 No.5

Time-varying mesh stiffness (TVMS) and the dynamic coupling between the helical gears have a great influence on the vibration characteristics of a helical gear rotor system. Considering the effects of TVMS and adopting two coupling models (lateral-torsional coupling model and lateral-torsional-axial-swing coupling model), the dynamic behavior of a helical gear system was studied. First, an analytical model was used to analyze TVMS of a helical gear pair where the helical tooth is simulated by many spur tooth slices along the direction of the tooth width and the mesh stiffness of each slice is calculated using the energy method. Then, considering the effects of the TVMS excitation, the finite element model of a helical gear rotor system was established. Gear mesh was simulated by the above-mentioned two coupling models to investigate the effects of coupling forms on the system vibration characteristics. The strain energy was used to distinguish the dominant mode and dominant shaft of a gear system in natural characteristics analysis. The results show that the full coupling model can analyze accurately the vibration characteristics of the system and the axial and swing motions cannot be ignored in vibration analysis. Finally, the effects of helix angle on TVMS and vibration responses of a helical gear system were also studied.

ON MEROMORPHIC SOLUTIONS OF NONLINEAR PARTIAL DIFFERENTIAL-DIFFERENCE EQUATIONS OF FIRST ORDER IN SEVERAL COMPLEX VARIABLES

Qibin Cheng,Yezhou Li,Zhixue Liu 대한수학회 2023 대한수학회보 Vol.60 No.2

This paper is concerned with the value distribution for meromorphic solutions $f$ of a class of nonlinear partial differential-difference equation of first order with small coefficients. We show that such solutions $f$ are uniquely determined by the poles of $f$ and the zeros of $f-c, f-d$ (counting multiplicities) for two distinct small functions $c, d$.

Analysis of Charging Stations’ Layout based on the Study about Electric Vehicle Routine Optimizing

Xiaochun Lu,Qibin Chen 보안공학연구지원센터 2014 International Journal of Control and Automation Vol.7 No.5

Dynamic analysis of three-dimensional helical geared rotor system with geometric eccentricity

Yimin Zhang,Qibin Wang,Hui Ma,Jing Huang,Chunyu Zhao 대한기계학회 2013 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.27 No.11

A dynamic model of a multi-shaft helical geared rotor system is presented. Rotating shafts of the system are modeled as Timoshenko beams. A general three-dimensional dynamic model of helical gear pairs with geometric eccentricity is developed for the gear mesh and bearing flexibility is included in the model as well. The transmission error and gear geometric eccentricity are simulated as excitations. Eigenvalue solution and the modal summation technique are used to predict the natural frequencies and forced responses of the system. Then two geared rotor system models are presented for validation of the gear dynamic model. It is demonstrated that the gear mesh model is effective for general geared rotor systems, spur and helical gears, one-stage and multi-stage systems. Finally, forced responses of an example system are analyzed to demonstrate the influences of the helical gear geometric eccentricity and the coupling between gear geometric eccentricity and rotor mass unbalance.

Tongue-Rudder: A Glossokinetic-Potential-Based Tongue–Machine Interface

Nam, Yunjun,Zhao, Qibin,Cichocki, Andrzej,Choi, Seungjin IEEE 2012 IEEE Transactions on Biomedical Engineering Vol.59 No.1

<P>Glossokinetic potentials (GKPs) are electric potential responses generated by tongue movement. In this study, we use these GKPs to automatically detect and estimate tongue positions, and develop a tongue-machine interface. We show that a specific configuration of electrode placement yields discriminative GKPs that vary depending on the direction of the tongue. We develop a linear model to determine the direction of tongue from GKPs, where we seek linear features that are robust to a baseline drift problem by maximizing the ratio of intertask covariance to intersession covariance. We apply our method to the task of wheelchair control, developing a tongue-machine interface for wheelchair control, referred to as tongue-rudder. A teeth clenching detection system, using electromyography, was also implemented in the system in order to assign teeth clenching as the stop command. Experiments on off-line cursor control and online wheelchair control confirm the unique advantages of our method, such as: 1) noninvasiveness, 2) fine controllability, and 3) ability to integrate with other EEG-based interface systems.</P>

On Private Enterprise`s Financing and Non-state-owned Financial Organization`s Fostering

Jiao, Fangyi,Yang, Qibin 한양대학교 경제연구소 2002 경제연구 Vol.23 No.1

In this thesis, we discuss the reasons causing private enterprise to face financing difficulty and the countermoves guiding it out of predicament. We believe that the high costs of loan to private enterprise contribute to national commercial bank's unwillingness to accommodate it with a loan. The financial deterioration and management disorder of some rural credit cooperatives cause the private enterprise to lose its important financing channel. The key to solve private enterprise's financing problem is to foster rural credit market and to set up shareholding and cooperative non-state-owned financial organization, participated by private enterprise. The financial structure under the planned economic system decides the basic characteristics of China's present financial system: The commercial bank of national sale ownership dominates a monopoly position in the financial system and possesses most of the market shares. More than seventy percent of social money resources are allocated to state -owned business through the national commercial bank --the main channel. Since the reform and opening up to the outside world, especially after I994, the reform of finance, taxation, foreign exchange and so on, the macro-economic management structure reform all- sided way. Shareholding commercial banks are established one after another, some of which have fairly strong ability to innovate: for example, Bank of Investment, through coming to the market to finance; some banks strengthen their capital power, broaden their business scope and get a rapid progress, such as Development Bank of Shenzhen, Development Bank of Pudong, Minsheng Bank. The rapid development of the shareholding commercial bank changes the structure of China's financial system, and adds vitality to the financial market. But they're at the growth stage, on the small scale and with few operating networks. Minsheng Bank is a non-state-owned financial institution in the strict sense. Before coming into the market, its registered capital is only about one billion yuan. The aggregate capital is only forty billion yuan or more, which cannot meet the needs of the high developing private enterprises.

A Method of Zero self-modification and Temperature Compensation for Indoor Air Quality Detection Based on a software Model

Cuiping Li,Jiuqiang Han,Qibin Huang,Xiaoqiang Dong,Xuequan Ding,Yaming Ding,Dianguo Zhang,Ning Mu 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10

It is very difficult to apply non-dispersive infrared sensor to detect the indoor air quality and maintain very low zero and temperature drift over long periods. Frequently manual zero setting and calibration are required. To solve the issues of zero and temperature drift of non-dispersive infrared sensor, a software model based on zero gas intensity, reference channels intensity, standard temperature, environmental temperature, temperature drift coefficient, etc. has been established to automatically modify and compensate the zero and temperature drift existing in the long-term continuous operation of the infrared sensor. The test result and long-term application indicate the detection precision of the instrument is less than 5%F.S in various changing environmental conditions. The average detection precision of carbon dioxide has been improved from 9.26% before comprehensive processing to 1.23% after processing, while the average detection precision of methane has been improved from 10.61% before comprehensive processing to 0.70% after processing. As a result, the disadvantages existing in many gas detectors including poor stability and short calibration cycle have been overcome, thus effectively improving the detection precision and stability of the instrument and reducing the maintenance cost.

The Development and Application of a External Coating for Buried Pipeline Rehabilitation

Zhang, Liping,Lin, Zhu,Zhang, Qibin,Qin, Yanlong,Wang, Xueying 한국부식방식학회 2003 Corrosion Science and Technology Vol.2 No.3

With the development of Chinese petroleum and gas industry, about 20,000 km long-distance pipeline and 250,000 km gathering pipeline have been constructed in China. After operating for many years, most of the coatings on buried pipelines have aged so severe that the steel pipes are subject to corrosion environment underground. Focusing on the need of extemal coating for buried pipeline rehabilitation, a new type of coating has been developed. The development and application of the coatings has been introduced in this paper.

A hybrid algorithm for reliability analysis combining Kriging and subset simulation importance sampling

Cao Tong,Zhili Sun,Qianli Zhao,Qibin Wang,Shuang Wang 대한기계학회 2015 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.29 No.8

To solve the problem of large computation when failure probability with time-consuming numerical model is calculated, we proposean improved active learning reliability method called AK-SSIS based on AK-IS algorithm [1]. First, an improved iterative stopping criterionin active learning is presented so that iterations decrease dramatically. Second, the proposed method introduces Subset simulationimportance sampling (SSIS) into the active learning reliability calculation, and then a learning function suitable for SSIS is proposed. Finally, the efficiency of AK-SSIS is proved by two academic examples from the literature. The results show that AK-SSIS requiresfewer calls to the performance function than AK-IS, and the failure probability obtained from AK-SSIS is very robust and accurate. Thenthis method is applied on a spur gear pair for tooth contact fatigue reliability analysis.