Multivariable modeling of valve inner leakage acoustic emission signal based on Gaussian process

• Published in: Mechanical systems and signal processing 2020-06, Vol.140, p.106675, Article 106675
• Main Authors: Ye, Guo-Yang, Xu, Ke-Jun, Wu, Wen-Kai
• Format: Article
• Language: English
• Subjects: Acoustic emission detection technology; Acoustic emission testing; Destructive testing; Emission analysis; Flow coefficients; Gauss process; Gaussian process; Internal leakage; Leak detection; Mathematical analysis; Mathematical models; Mean square errors; Multivariable mathematical model; Nondestructive testing; Polynomials; Regression analysis; Root-mean-square errors; Signal processing; Statistical analysis; Support vector machines; Valve
• ISSN: 0888-3270; 1096-1216
• DOI: 10.1016/j.ymssp.2020.106675

Three-dimensional graph of standard deviation, leakage rate and pressure. [Display omitted] •The experimental setup has been improved.•The experiments of the valve leakage detection are performed.•A multivariate mathematical model is established.•The probability distribution of leakage rate is obtained.•The modeling results of various methods are compared. As a non-destructive testing method, acoustic emission (AE) technology can be used for internal leakage detection of valve on-line. In order to enhance the practicability of valve leakage detection by AE technology and realize valve leakage detection under various pressure conditions, the Gaussian process regression (GPR) is used to establish a multivariate mathematical model for describing the relationship between the characteristic of AE signal and the pressure, leakage rate. Based on the mathematical model built by GPR, we can not only determine leakage rate, but also obtain the probability distribution of leakage rate according to the predicted mean and standard deviation. In order to verify the modeling effect of GPR, the analysis results are compared with those of least squares linear regression, polynomial regression and support vector machine regression. For the HTS50-17 valve, the root mean square error of GPR is the smallest, which is 22.6948 ml/min. Moreover, the fitting degree of the GPR is greatest, which is 0.9653. On this basis, in order to improve the universality of valve leakage AE detection, the mixed experimental data of different flow coefficient of the same type valve are analyzed, and the root mean square error of GPR is the smallest, which is 23.0646 ml/min. It is indicated that GPR can achieve better results for the AE signal of valve leakage.