Analyzing failure modes using RBDs in Weibull++

Features          Training          Demo          Request quote          Resources
ReliaSoft Weibull++ provides the ability to use a reliability block diagram (RBD) to model series, parallel and k-out-of-n configurations. In this article, we will give an example of how to use an RBD to conduct failure modes analysis.

Introduction

An electronic device can fail due to six independent primary failure modes: A, B, C, D, E and F. The component fails if mode A, mode B or mode F occurs. If mode C, mode D or mode E occurs alone, the component does not fail; however, the component will fail if any two (or more) of these modes occur (i.e., C and D; D and E; E and C; or C, D and E). The objective is to analyze each data set using the 2-parameter Weibull distribution with MLE and to determine the lower 1-sided 90% confidence interval on the reliability of this component at 100 hours.
ReliaSoft Weibull++ provides the ability to use a reliability block diagram (RBD) to model series, parallel and k-out-of-n configurations. In this article, we will give an example of how to use an RBD to conduct failure modes analysis.

Introduction

An electronic device can fail due to six independent primary failure modes: A, B, C, D, E and F. The component fails if mode A, mode B or mode F occurs. If mode C, mode D or mode E occurs alone, the component does not fail; however, the component will fail if any two (or more) of these modes occur (i.e., C and D; D and E; E and C; or C, D and E). The objective is to analyze each data set using the 2-parameter Weibull distribution with MLE and to determine the lower 1-sided 90% confidence interval on the reliability of this component at 100 hours.

Experiment and data

The following tables present the time-to-failure data for these modes (in hours).

 Mode A Mode B Mode C Number State Time Number State Time Number State Time in Group in Group in Group 1 F 1144 1 F 2221 1 F 19 1 F 1719 1 F 2257 1 F 140 1 F 2129 1 F 2569 1 F 292 1 F 2803 1 F 3029 1 F 432 1 F 3020 1 F 3805 1 F 528 1 F 3082 10 S 5000 1 F 552 1 F 3589 1 F 605 1 F 3973 1 F 734 1 F 4337 1 F 779 1 F 5011 1 F 874 1 F 5029 18 S 5500 Mode D Mode E Mode F Number State Time Number State Time Number State Time in Group in Group in Group 1 F 1063 1 F 1290 1 F 605 1 F 1085 1 F 2261 1 F 760 1 F 1399 1 F 2355 1 F 773 1 F 1445 1 F 3209 1 F 854 1 F 1550 1 F 3284 1 F 890 1 F 2056 1 F 3394 1 F 1165 1 F 4384 1 F 3596 1 F 1220 1 F 4863 1 F 4203 1 F 1320 8 S 5000 1 F 4254 1 F 1967 1 F 4294 1 F 2606 1 F 4420 1 F 2834 10 S 5000 15 S 3000

Analysis

Step 1: Using Weibull++, the first step is to create a new data sheet for grouped times-to-failure data with suspensions.

Step 2: Rename the folio to "Component" and the data sheet to "Mode A." Enter the data given for Mode A and use the 2-parameter Weibull distribution with MLE to calculate the parameters, as shown next.

Step 3: Insert another data sheet of the same type named "Mode B," enter the data given for Mode B and calculate the parameters. Repeat for the remaining failure modes.

Step 4: Choose Home > Insert > Diagram.

Step 5: Build the RBD that describes the reliability-wise configuration of the failure modes, as shown next.

Note that the node in the diagram requires 2 of the 3 paths to succeed.

Step 6: Click Calculate to analyze the diagram.

Then use the Quick Calculation Pad (QCP) to calculate the reliability at 100 hours with the lower 1-sided 90% confidence bound, as shown next.

The lower bound is estimated to be 96.71%.