Entity

Time filter

Source Type

Chengdu, China

Zhi Z.,Sichuan Sunny Seal Co. | Xiaohui L.,Southwest Jiaotong University
Proceedings - 2014 6th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2014 | Year: 2014

Mechanical seals operates by a thin fluid film to separate the pair of seal faces. The thickness of this film must be optimized for preventing the friction of two end faces and minimizing the leakage. In this study, the fluid film is measured by eddy current and acoustic emission techniques, and the data of eddy current are used to direct the processing of acoustic emission signal. To decrease the noise, wavelet packet and kernel principal component analysis are used to extract the data features. Then cascaded decision is presented to improve the recognition rate of artificial neural network, by which the film thickness can be estimated. © 2014 IEEE. Source


Liu Y.,University of Sichuan | Yin G.,University of Sichuan | Du J.,Sichuan University | Zhang Z.,Sichuan Sunny Seal Co.
Sichuan Daxue Xuebao (Gongcheng Kexue Ban)/Journal of Sichuan University (Engineering Science Edition) | Year: 2016

For the stability of gas film thickness and multistage regulation operating conditions leading to failure in dry gas seal, the dynamic characteristics of dry gas seal with spiral groove were analyzed based on Workbench. A model of axial vibration of a floating ring(static ring) was established, and the expression of axial vibration amplitude was derived. Workbench was applied to finish prestressed modal analysis and harmonic response analysis of the floating ring system under working conditions. The simulation was compared with the results of theoretical derivation. The change trend of axial vibration amplitude of the floating ring was got under the same parameters with different values, and the main and minor factors affecting the axial vibration amplitude of the floating ring were distinguished. This approach not only obtained the values of the amplitude of floating ring under different conditions flexibly, but also explained the trend of vibration from the relationship between vibration frequency and inherent frequency. © 2016, Editorial Department of Journal of Sichuan University (Engineering Science Edition). All right reserved. Source


Li X.,Southwest Jiaotong University | Fu P.,Southwest Jiaotong University | Chen K.,Sichuan Sunny Seal Co. | Lin Z.,Southwest Jiaotong University | Zhang E.,Southwest Jiaotong University
Shock and Vibration | Year: 2016

Monitoring the contact state of seal end faces would help the early warning of the seal failure. In the acoustic emission (AE) detection for mechanical seal, the main difficulty is to reduce the background noise and to classify the dispersed features. To solve these problems and achieve higher detection rates, a new approach based on genetic particle filter with autoregression (AR-GPF) and hypersphere support vector machine (HSSVM) is presented. First, AR model is used to build the dynamic state space (DSS) of the AE signal, and GPF is used for signal filtering. Then, multiple features are extracted, and a classification model based on HSSVM is constructed for state recognition. In this approach, AR-GPF is an excellent time-domain method for noise reduction, and HSSVM has advantage on those dispersed features. Finally experimental data shows that the proposed method can effectively detect the contact state of the seal end faces and has higher accuracy rates than some other existing methods. © 2016 Xiaohui Li et al. Source


Li X.-H.,Southwest Jiaotong University | Fu P.,Southwest Jiaotong University | Cao W.-Q.,Southwest Jiaotong University | Chen K.,Sichuan Sunny Seal Co.
Zhendong yu Chongji/Journal of Vibration and Shock | Year: 2016

Monitoring the contact state of seal-end faces would help to the early warning of the seal failure. For the problem of the difficulty in seal signal denoising, a new approach based on particle filtering with artificial neural network (ANN-PF) and least square support vector machine (LS-SVM) is presented for acoustic emission (AE) modeling. After measuring seal film thickness, variations of the AE energy during the seal startup are studied. Then, Elman ANN is used to build the dynamic state space (DSS) of the AE signal, and PF is used for signal filtering. Finally, multiple features are extracted and a classification model based on LS-SVM is constructed for state monitoring. Experimental data shows that the proposed method can detect the seal face contact effectively and non-destructively, and it has extensive industrial prospects. © 2016, Editorial Office of Journal of Vibration and Shock. All right reserved. Source


Li X.,Southwest Jiaotong University | Fu P.,Southwest Jiaotong University | Zhang Z.,Sichuan Sunny Seal Co.
Sichuan Daxue Xuebao (Gongcheng Kexue Ban)/Journal of Sichuan University (Engineering Science Edition) | Year: 2014

Mechanical seals is operated by a thin fluid film to separate the pair of seal faces for lubricating and sealing, so the film thickness needs to be measured. Because the current technique is not suit for industry, a method for measurement of film thickness of mechanical seals based on acoustic emission technique was presented. Through the direction of direct measurement, a detection model based on acoustic emission signal was built. First, the signal was processed by empirical mode decomposition, and kernel principal component analysis was used to optimize data features. Then, a cascaded decision model based on artificial neural network was presented to estimate the film thickness. The model has better recognition rate than a single neural network, and has a wide industrial prospect. ©, 2014, Sichuan Daxue Xuebao (Gongcheng Kexue Ban)/Journal of Sichuan University (Engineering Science Edition). All right reserved. Source

Discover hidden collaborations