Reliability Improvement with Design of Experiments

Condra, Lloyd W.

doi:10.1201/9781482270846-21

Cited by 19 publications

(31 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Design of Experiments (DOE) is third method that has been described extensively in literature in relation to reliability [CON01]. Special attention should be given to an experiment performed by Tseng, Hamada and Chiao [TSE94].…”

Section: Literature Reviewmentioning

confidence: 99%

A method for reliability optimization through degradation analysis and robust design

Bogaard

Shreeram

Brombacher

Annual Reliability and Maintainability Symposium, 2003.

View full text Add to dashboard Cite

Given the strong drive to achieve a short time to market with strongly innovative products many companies face a structural dilemma with respect to product reliability. Due to the increasing complexity of products and the way they are applied, longer and increasingly complex tests are required to establish (and if necessary optimize) the reliability of these products. On the other hand, due to the strong pressure on "Time to Market" in many design processes, this time is simply not available. Therefore alternative strategies have to be developed. This paper addresses a strategy to replace reliability tests by reliability optimization based on computer simulations. Although the development of adequate models is, in a practical situation, quite complex and time consuming as well, once these models are available they can lead to considerable shorter product development cycles. INTRODUCTIONReliability of consumer products has always been a big concern for manufacturers. Customers expect to use products over a certain period of time without any problems. This leads to the problem of addressing the risks involved in perceived quality and reliability levels and if possible control or reduce them at the design phase. In the early phases of the design development, actual field information of the product function will not be available. Therefore, predictive models for the product design must be developed in order to allow an assessment of its behavior in the field. It is only through this that it is possible to realize the early identification and resolution of potential quality and reliability problems. In this paper a new concept for designing for reliability will be presented and illustrated by a simulation example. First a brief discussion on the purpose of the paper will be presented, followed by the background of the research. In the next part a literature review of existing methods in reliability engineering will be discussed, followed by the problem discussion. The next section will describe the general line of research emphasizing on theory and the approach used. The theory developed is tested using simulation techniques. Then the results and conclusions are explained followed by a research discussion.2.0 PURPOSE OF RESEARCH Reliability theory deals with the interdisciplinary use of probability, statistics, and stochastic modeling, combined with engineering insights into the design and the scientific understanding of the failure mechanisms, to study the various aspects of reliability [BLI00]. This is also very true for the concept as will be discussed in this paper.The proposed concept basically tries to solve a reliability improvement-optimization problem through analysis and modeling of degradation of the critical designable parameters or design parameters (= physical product parameters that can be influenced by the designer) and associating it with the degradation of the performance characteristic under study, where performance characteristic can be defined as a measure expressing how good a product fulfils its...

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A method for reliability optimization through degradation analysis and robust design

Bogaard

Shreeram

Brombacher

Annual Reliability and Maintainability Symposium, 2003.

View full text Add to dashboard Cite

show abstract

“…Designs which violate the reliability requirement are shaded without further consideration. (5) 3, 1 0.99843184 (7) 0.000844558 (7) 3, 2 0.99826944 (9) 0.000458715 (1) 3, 3 0.99823600 (10) 0.000824949 (6) 3, 4 0.99755964 (12) 0.000771504 (4) Obviously, to maximize the system reliability, the optimum choice will be [Lf=1, Wf=1, Lr=1, Wr=1] by allocating the highest reliable component types to the corresponding subsystems. However, such a system will exhibit poor robustness with the highest reliability variance of 0.000947179.…”

Section: Applicationmentioning

confidence: 99%

Optimization of system reliability robustness using accelerated degradation testing

Liao

Elsayed

Annual Reliability and Maintainability Symposium, 2005. Proceedings.

View full text Add to dashboard Cite

In the system design stage, several component types (or modules) with competitive reliability are usually available for the design of each subsystem; however, their robustness against uncertain operating conditions might be significantly different. Designers attempt to address the design of a reliable and robust system by choosing the "best" components from those candidates. The problem is more difficult when constructing reliable systems with highly reliable components due to the difficulty of evaluating the reliability and robustness of such components under normal operating conditions. In this paper, we investigate a 3-step procedure for system optimization regarding the reliability robustness through Accelerated Degradation Testing (ADT) experiments. In the first step, baseline ADT experiments are conducted to obtain degradation data for each degradable component type of interest using a small number of test units. In this step, an ADT model along with the parameters of each component type is estimated based on the initial data (baseline data). The second step refines the estimation accuracy of those critical model parameters by designing an optimum ADT plan. The optimum testing plan belongs to a D-optimal plan which minimizes the determinant of the variance-covariance matrix of the parameter estimates. Finally, in the third step the reliabilities of alternative component types are predicted under nominal operating conditions and their robustness is evaluated considering the uncertainty of the operating conditions. The design procedure is demonstrated using an example of a brake system design. RAMS 200548 0-7803-8824-0/05/$20.00 ©2005 IEEE

show abstract

“…PARAMETER TOLERANCE DESIGN To determine the design parameter's tolerances, we need to establish the relationship between the variance function of y(t) and the variances of the design parameters. In this section, we consider how to use Equations (12) and (13) to establish the variance model.…”

Section: Kijmentioning

confidence: 99%

“…Using the linear and interaction effect model Equation (12) The data analysis process in tk, k=1,2,3,4,5, is illustrated by and sum-of squares decomposition model (Equation 13), we t2=80hr: different parameter sets are shown in Fig A-1.…”

Section: (B) the Variance Corresponding To Interactionsmentioning

confidence: 99%

“…In the main and interaction effect model, a linear effect parameters corresponds to a linear term; and a quadratic effect parameter corresponds to a square term. Quadratic effect parameterHere we assume that the design parameters x,, i=1,2, ..., wl are linear effects parameters; and the design parameters x,, i= wl+l, ..., w, are qu<adratic effect parameters.. Equations(12) and(13), we want to establish the relationship between variance of y and variances of…”

mentioning

confidence: 99%

See 1 more Smart Citation