Life Data Classification - Revision history

Lisa Hacker: /* Fractional Failures */

2023-03-09T00:54:08Z

Fractional Failures

← Older revision		Revision as of 00:54, 9 March 2023
Line 89:		Line 89:
	\|- align="center"		\|- align="center"
	\|1 \|\|F \|\| 290		\|1 \|\|F \|\| 290
	\|\|- align="center"		\|- align="center"
	\|1 \|\|F \|\| 410		\|1 \|\|F \|\| 410
	\|}		\|}

Lisa Hacker: /* Fractional Failures */

2023-03-09T00:53:40Z

Fractional Failures

← Older revision		Revision as of 00:53, 9 March 2023
Line 62:		Line 62:
	\|- align="center"		\|- align="center"
	\|1 \|\|F \|\| 105		\|1 \|\|F \|\| 105
	\|-		\|- align="center"
	\|0.4 \|\|F \|\| 168		\|0.4 \|\|F \|\| 168
	\|-		\|- align="center"
	\|1 \|\|F \|\| 220		\|1 \|\|F \|\| 220
	\|-		\|- align="center"
	\|1 \|\|F \|\| 290		\|1 \|\|F \|\| 290
	\|-		\|- align="center"
	\|1 \|\|F \|\| 410		\|1 \|\|F \|\| 410
	\|}		\|}
Line 81:		Line 81:
	\|- align="center"		\|- align="center"
	\|1 \|\|F \|\| 105		\|1 \|\|F \|\| 105
	\|-		\|- align="center"
	\|0.4 \|\|F \|\| 168		\|0.4 \|\|F \|\| 168
	\|-		\|- align="center"
	\|0.6 \|\|S \|\| 168		\|0.6 \|\|S \|\| 168
	\|-		\|- align="center"
	\|1 \|\|F \|\| 220		\|1 \|\|F \|\| 220
	\|-		\|- align="center"
	\|1 \|\|F \|\| 290		\|1 \|\|F \|\| 290
	\|-		\|\|- align="center"
	\|1 \|\|F \|\| 410		\|1 \|\|F \|\| 410
	\|}		\|}
Line 104:		Line 104:
	\|- align="center"		\|- align="center"
	\|1 \|\|F \|\| 105 \|\| 1 \|\|12.945		\|1 \|\|F \|\| 105 \|\| 1 \|\|12.945
	\|-		\|- align="center"
	\|0.4 \|\|F \|\| 168 \|\| 1.4 \| 20.267		\|0.4 \|\|F \|\| 168 \|\| 1.4 \| 20.267
	\|-		\|- align="center"
	\|0.6 \|\|S \|\| 168\|\| \|\|		\|0.6 \|\|S \|\| 168\|\| - \|\| -
	\|-		\|- align="center"
	\|1 \|\|F \|\| 220 \|\| 2.55 \|\| 41.616		\|1 \|\|F \|\| 220 \|\| 2.55 \|\| 41.616
	\|-		\|- align="center"
	\|1 \|\|F \|\| 290 \|\| 3.7 \|\| 63.039		\|1 \|\|F \|\| 290 \|\| 3.7 \|\| 63.039
	\|-		\|- align="center"
	\|1 \|\|F \|\| 410 \|\| 4.85 \|\| 84.325		\|1 \|\|F \|\| 410 \|\| 4.85 \|\| 84.325
	\|}		\|}

Lisa Hacker: /* Fractional Failures */

2023-03-09T00:52:12Z

Fractional Failures

@@ Line 53: / Line 53: @@
 After the completion of a reliability test or after failures are observed in the field, a redesign can be implemented to improve a product’s reliability. After the redesign, and before new failure data become available, it is often times desirable to “adjust” the reliability that was calculated from the previous design and take “credit” for this theoretical improvement. This can be achieved with fractional failures. Using past experience to estimate the effectiveness of a corrective action or redesign, an analysis can take credit for this improvement by adjusting the failure count. Therefore, if a corrective action on a failure mode is believed to be 70% effective, then the failure count can be reduced from 1 to 0.3 to reflect the effectiveness of the corrective action.
-<!--For example, consider the following data set.
+For example, consider the following data set.
 In this case, a design change has been implemented for the failure mode that occurred at 168 hours and is assumed to be 60% effective. In the background, Weibull++ converts this data set to:
-::<math>\begin{matrix}
+{| border="1" align="center" style="border-collapse: collapse;" cellpadding="5" cellspacing="5"
-   Number in State & State F or S & State End Time (Hr)  \\
+|- align="center"
-& F & 105  \\
+!Number in State
-.4 & F & 168  \\
+!State F or S
-.6 & S & 168  \\
+!State End Time (Hr)
-& F & 220  \\
+|- align="center"
-& F & 290  \\
+|1 ||F || 105
-& F & 410  \\
+|-
-\end{matrix}\,\!</math>
+|0.4 ||F || 168
-If [[Parameter Estimation|Rank Regression]] is used to estimate distribution parameters, the median ranks for the previous data set are calculated as follows:
+{| border="1" align="center" style="border-collapse: collapse;" cellpadding="5" cellspacing="5"
 Given this information, the standard Rank Regression procedure is then followed to estimate parameters.

Lisa Hacker: /* Fractional Failures */

2023-03-09T00:35:51Z

Fractional Failures

← Older revision		Revision as of 00:35, 9 March 2023
Line 53:		Line 53:
	After the completion of a reliability test or after failures are observed in the field, a redesign can be implemented to improve a product’s reliability. After the redesign, and before new failure data become available, it is often times desirable to “adjust” the reliability that was calculated from the previous design and take “credit” for this theoretical improvement. This can be achieved with fractional failures. Using past experience to estimate the effectiveness of a corrective action or redesign, an analysis can take credit for this improvement by adjusting the failure count. Therefore, if a corrective action on a failure mode is believed to be 70% effective, then the failure count can be reduced from 1 to 0.3 to reflect the effectiveness of the corrective action.		After the completion of a reliability test or after failures are observed in the field, a redesign can be implemented to improve a product’s reliability. After the redesign, and before new failure data become available, it is often times desirable to “adjust” the reliability that was calculated from the previous design and take “credit” for this theoretical improvement. This can be achieved with fractional failures. Using past experience to estimate the effectiveness of a corrective action or redesign, an analysis can take credit for this improvement by adjusting the failure count. Therefore, if a corrective action on a failure mode is believed to be 70% effective, then the failure count can be reduced from 1 to 0.3 to reflect the effectiveness of the corrective action.

	For example, consider the following data set.		<!--For example, consider the following data set.

	::<math>\begin{matrix}		::<math>\begin{matrix}
Line 90:		Line 90:
	\end{matrix}\,\!</math>		\end{matrix}\,\!</math>

			-->
	Given this information, the standard Rank Regression procedure is then followed to estimate parameters.		Given this information, the standard Rank Regression procedure is then followed to estimate parameters.

Nicolette Young: /* Example */

2015-12-16T17:11:10Z

Example

← Older revision		Revision as of 17:11, 16 December 2015
Line 110:		Line 110:
	The following overlay plot of unreliability vs. time shows that by using fractional failures the estimated unreliability of the component has decreased, while the B10 life has increased from 2,566 hours to 3,564 hours.		The following overlay plot of unreliability vs. time shows that by using fractional failures the estimated unreliability of the component has decreased, while the B10 life has increased from 2,566 hours to 3,564 hours.

	[[Image:Fractional Failures 4.png\|center\|~~600px~~\| ]]		[[Image:Fractional Failures 4.png\|center\|650px\| ]]

Nicolette Young: /* Example */

2015-12-16T17:10:32Z

Example

← Older revision		Revision as of 17:10, 16 December 2015
Line 100:		Line 100:
	A component underwent a reliability test. 12 samples were run to failure. The following figure shows the failures and the analysis in a Weibull++ standard folio.		A component underwent a reliability test. 12 samples were run to failure. The following figure shows the failures and the analysis in a Weibull++ standard folio.

	[[Image:Fractional Failures 1.png\|center\|~~600px~~\| ]]		[[Image:Fractional Failures 1.png\|center\|700px\| ]]


	The analysts believe that the planned design improvements will yield 50% effectiveness. To estimate the reliability of the product based on the assumptions about the repair effectiveness, they enter the data in groups, counting a 0.5 failure for each group. The following figure shows the adjusted data set and the calculated parameters.		The analysts believe that the planned design improvements will yield 50% effectiveness. To estimate the reliability of the product based on the assumptions about the repair effectiveness, they enter the data in groups, counting a 0.5 failure for each group. The following figure shows the adjusted data set and the calculated parameters.

	[[Image:Fractional Failures 2.png\|center\|~~600px~~\| ]]		[[Image:Fractional Failures 2.png\|center\|700px\| ]]

Nicolette Young: /* Example */

2015-12-16T17:10:13Z

Example

← Older revision		Revision as of 17:10, 16 December 2015
Line 100:		Line 100:
	A component underwent a reliability test. 12 samples were run to failure. The following figure shows the failures and the analysis in a Weibull++ standard folio.		A component underwent a reliability test. 12 samples were run to failure. The following figure shows the failures and the analysis in a Weibull++ standard folio.

	[[Image:Fractional Failures 1.png\|center\|~~450px~~\| ]]		[[Image:Fractional Failures 1.png\|center\|600px\| ]]


	The analysts believe that the planned design improvements will yield 50% effectiveness. To estimate the reliability of the product based on the assumptions about the repair effectiveness, they enter the data in groups, counting a 0.5 failure for each group. The following figure shows the adjusted data set and the calculated parameters.		The analysts believe that the planned design improvements will yield 50% effectiveness. To estimate the reliability of the product based on the assumptions about the repair effectiveness, they enter the data in groups, counting a 0.5 failure for each group. The following figure shows the adjusted data set and the calculated parameters.

	[[Image:Fractional Failures 2.png\|center\|~~450px~~\| ]]		[[Image:Fractional Failures 2.png\|center\|600px\| ]]


	The following overlay plot of unreliability vs. time shows that by using fractional failures the estimated unreliability of the component has decreased, while the B10 life has increased from 2,566 hours to 3,564 hours.		The following overlay plot of unreliability vs. time shows that by using fractional failures the estimated unreliability of the component has decreased, while the B10 life has increased from 2,566 hours to 3,564 hours.

	[[Image:Fractional Failures 4.png\|center\|~~450px~~\| ]]		[[Image:Fractional Failures 4.png\|center\|600px\| ]]

Kate Racaza: /* Fractional Failures */

2015-05-22T17:55:05Z

Fractional Failures

← Older revision		Revision as of 17:55, 22 May 2015
Line 51:		Line 51:
	==Fractional Failures==		==Fractional Failures==

	After the completion of a reliability test or after failures are observed in the field, a redesign can be implemented to improve ~~the~~ product’s reliability. After the redesign, and before new failure data become available, it is often times desirable to “adjust” the reliability that was calculated from the previous design and take “credit” for this theoretical improvement. This can be achieved with fractional failures. Using past experience to estimate the effectiveness of a corrective action or redesign, an analysis can take credit for this improvement by adjusting the failure count. Therefore, if a corrective action on a failure mode is believed to be 70% effective, then the failure count can be reduced from 1 to 0.3 to ~~indicate that~~.		After the completion of a reliability test or after failures are observed in the field, a redesign can be implemented to improve a product’s reliability. After the redesign, and before new failure data become available, it is often times desirable to “adjust” the reliability that was calculated from the previous design and take “credit” for this theoretical improvement. This can be achieved with fractional failures. Using past experience to estimate the effectiveness of a corrective action or redesign, an analysis can take credit for this improvement by adjusting the failure count. Therefore, if a corrective action on a failure mode is believed to be 70% effective, then the failure count can be reduced from 1 to 0.3 to reflect the effectiveness of the corrective action.

	For example, consider the following data set.		For example, consider the following data set.
Line 77:		Line 77:
	\end{matrix}\,\!</math>		\end{matrix}\,\!</math>

	~~===Rank Regression===~~

	If [[Parameter Estimation\|Rank Regression]] is used to estimate distribution parameters, the median ranks for the previous data set are calculated as follows:		If [[Parameter Estimation\|Rank Regression]] is used to estimate distribution parameters, the median ranks for the previous data set are calculated as follows:
Line 94:		Line 93:
	Given this information, the standard Rank Regression procedure is then followed to estimate parameters.		Given this information, the standard Rank Regression procedure is then followed to estimate parameters.

	~~===~~Maximum Likelihood Estimation~~===~~		If [[Maximum Likelihood Estimation\|Maximum Likelihood Estimation (MLE)]] is used to estimate distribution parameters, the grouped data likelihood function is used with the number in group being a non-integer value.

	If [[Maximum Likelihood Estimation\|Maximum Likelihood Estimation (MLE)]] is used to estimate distribution parameters, the grouped data likelihood function is used with the number in group being a non-integer value.

	===Example===		===Example===

Athanasios Gerokostopoulos: /* Fractional Failures */

2015-05-22T16:48:31Z

Fractional Failures

← Older revision		Revision as of 16:48, 22 May 2015
Line 97:		Line 97:

	If [[Maximum Likelihood Estimation\|Maximum Likelihood Estimation (MLE)]] is used to estimate distribution parameters, the grouped data likelihood function is used with the number in group being a non-integer value.		If [[Maximum Likelihood Estimation\|Maximum Likelihood Estimation (MLE)]] is used to estimate distribution parameters, the grouped data likelihood function is used with the number in group being a non-integer value.

			===Example===

			A component underwent a reliability test. 12 samples were run to failure. The following figure shows the failures and the analysis in a Weibull++ standard folio.

			[[Image:Fractional Failures 1.png\|center\|450px\| ]]


			The analysts believe that the planned design improvements will yield 50% effectiveness. To estimate the reliability of the product based on the assumptions about the repair effectiveness, they enter the data in groups, counting a 0.5 failure for each group. The following figure shows the adjusted data set and the calculated parameters.

			[[Image:Fractional Failures 2.png\|center\|450px\| ]]


			The following overlay plot of unreliability vs. time shows that by using fractional failures the estimated unreliability of the component has decreased, while the B10 life has increased from 2,566 hours to 3,564 hours.

			[[Image:Fractional Failures 4.png\|center\|450px\| ]]

Athanasios Gerokostopoulos at 16:28, 22 May 2015

2015-05-22T16:28:14Z

← Older revision		Revision as of 16:28, 22 May 2015
Line 48:		Line 48:

	If the objective of the analysis is to determine the probability of failure of the product, regardless of the mode responsible for the failure, we would analyze the data with all data entries classified as failures (complete data). However, if the objective of the analysis is to determine the probability of failure of the product due to Mode A only, we would then choose to treat failures due to Modes B or C as suspension (right censored) data. Those data points would be treated as suspension data with respect to Mode A because the product operated until the recorded time without failure due to Mode A.		If the objective of the analysis is to determine the probability of failure of the product, regardless of the mode responsible for the failure, we would analyze the data with all data entries classified as failures (complete data). However, if the objective of the analysis is to determine the probability of failure of the product due to Mode A only, we would then choose to treat failures due to Modes B or C as suspension (right censored) data. Those data points would be treated as suspension data with respect to Mode A because the product operated until the recorded time without failure due to Mode A.

			==Fractional Failures==

			After the completion of a reliability test or after failures are observed in the field, a redesign can be implemented to improve the product’s reliability. After the redesign, and before new failure data become available, it is often times desirable to “adjust” the reliability that was calculated from the previous design and take “credit” for this theoretical improvement. This can be achieved with fractional failures. Using past experience to estimate the effectiveness of a corrective action or redesign, an analysis can take credit for this improvement by adjusting the failure count. Therefore, if a corrective action on a failure mode is believed to be 70% effective, then the failure count can be reduced from 1 to 0.3 to indicate that.

			For example, consider the following data set.

			::<math>\begin{matrix}
			Number in State & State F or S & State End Time (Hr) \\
			1 & F & 105 \\
			0.4 & F & 168 \\
			1 & F & 220 \\
			1 & F & 290 \\
			1 & F & 410 \\
			\end{matrix}\,\!</math>


			In this case, a design change has been implemented for the failure mode that occurred at 168 hours and is assumed to be 60% effective. In the background, Weibull++ converts this data set to:

			::<math>\begin{matrix}
			Number in State & State F or S & State End Time (Hr) \\
			1 & F & 105 \\
			0.4 & F & 168 \\
			0.6 & S & 168 \\
			1 & F & 220 \\
			1 & F & 290 \\
			1 & F & 410 \\
			\end{matrix}\,\!</math>

			===Rank Regression===

			If [[Parameter Estimation\|Rank Regression]] is used to estimate distribution parameters, the median ranks for the previous data set are calculated as follows:

			::<math>\begin{matrix}
			Number in State & State F or S & State End Time (Hr) & MON & Median Rank (%) \\
			1 & F & 105 & 1 & 12.945 \\
			0.4 & F & 168 & 1.4 & 20.267 \\
			0.6 & S & 168 & & \\
			1 & F & 220 & 2.55 & 41.616 \\
			1 & F & 290 & 3.7 & 63.039 \\
			1 & F & 410 & 4.85 & 84.325 \\
			\end{matrix}\,\!</math>


			Given this information, the standard Rank Regression procedure is then followed to estimate parameters.

			===Maximum Likelihood Estimation===

			If [[Maximum Likelihood Estimation\|Maximum Likelihood Estimation (MLE)]] is used to estimate distribution parameters, the grouped data likelihood function is used with the number in group being a non-integer value.