Doctoral Dissertations


Zhengwei Hu

Keywords and Phrases

Machine learning; Outsourcing; Partial safety factor; Reliability analysis; Statistical modeling; Support vector machine


"The current business model for many industrial firms is to function as system integrators, depending on numerous outsourced components from outside component suppliers. This practice has resulted in tremendous cost savings; it makes system reliability analysis, however, more challenging due to the limited component information available to system designers. The component information is often proprietary to component suppliers. Motivated by the need of system reliability prediction with outsourced components, this work aims to explore feasible ways to accurately predict the system reliability during the system design stage. Four methods are proposed. The first method reconstructs component reliability functions using limited reliability data with respect to component loads, and the system reliability is then estimated statistically. The second method applies two-class support vector machines (SVM) to approximate limit-state functions of outsourced components based on the categorical reliability dataset. With the integration of the obtained limit-state functions and those of in-house components, the joint probability density function of all the components is estimated, thereby leading to accurate system reliability prediction. The third method is an extension of the second one, and a one-class SVM is proposed to rebuild limit-state functions for outsourced components given only the failure dataset. The last method deals with the case where no reliability dataset is available. A partial safety factor method is developed, which enables component suppliers to provide sufficient information to system designers for accurate reliability analysis without revealing the proprietary design details. Both numerical examples and engineering applications demonstrate the accuracy and effectiveness of the proposed methods"--Abstract, page iv.


Du, Xiaoping

Committee Member(s)

Chandrashekhara, K.
Dharani, Lokeswarappa R.
Hosder, Serhat
Conrad, Daniel


Mechanical and Aerospace Engineering

Degree Name

Ph. D. in Mechanical Engineering


National Science Foundation (U.S.)
Missouri University of Science and Technology. Intelligent Systems Center


The authors are grateful for the support from the National Science Foundation through grants CMMI 1234855 and CMMI 1300870 and CMMI 1562593.

Research Center/Lab(s)

Intelligent Systems Center


Missouri University of Science and Technology

Publication Date

Spring 2019

Journal article titles appearing in thesis/dissertation

  • System reliability prediction with shared load and unknown component design details
  • Integration of statistics- and physics-based methods -- A feasibility study on accurate system reliability prediction
  • One-class support vector machines with a bias constraint and its application in system reliability prediction
  • A partial safety factor method for system reliability prediction with outsourced components


xiv, 144 pages

Note about bibliography

Includes bibliographic references.


© 2019 Zhengwei Hu, All rights reserved.

Document Type

Dissertation - Open Access

File Type




Thesis Number

T 11533

Electronic OCLC #