Ученый
Старожил
Коллеги, столкнулся с ситуацией "Век живи - век учись" 
Обсуждается русский эквивалент термина Suspension (с определением: A test or operational unit that has not failed by the mode under consideration at the time of the life data analysis) в статистическом анализе результатов испытаний на долговечность.
В принципе он используется и в области гарантийных обязательств, например:
......Warranty data analysis relies on the estimation of a failure distribution based on data including the age and number of returns and the age and number of surviving units in the field. When working in the time domain, this is relatively simple, as one has knowledge of the time a part failed or survived as of the analysis date. When the driving factor of reliability is usage rather than time, however, the analysis becomes more involved.
There are many applications in which failures are dependent upon usage, not time. For example, in the automotive industry, the failure behavior in the majority of the products is mileage-dependent rather than time-dependent. These kinds of products present a challenge for data analysis. For surviving units still working in the field, how do we know their usage (“life”) and how do we incorporate it into the estimation of the failure distribution?
Suppose that you have been collecting sales (units in service) and returns data. For the returns data, you can determine the number of failures and their usage (by reading the odometer value, for example). Determining the number of surviving units Arrow (suspensions)......
Я посмотрел книжки. По смыслу подходят: в теории вероятностей - "Дополнение", в математике - "Надстройка". Физический смысл: дополнение "Выборки" (Sample) до полной совокупности событий. Но что-то нет уверенности в такой трактовке, может кто более плотно сталкивался с этим понятием??
Обсуждается русский эквивалент термина Suspension (с определением: A test or operational unit that has not failed by the mode under consideration at the time of the life data analysis) в статистическом анализе результатов испытаний на долговечность.
В принципе он используется и в области гарантийных обязательств, например:
......Warranty data analysis relies on the estimation of a failure distribution based on data including the age and number of returns and the age and number of surviving units in the field. When working in the time domain, this is relatively simple, as one has knowledge of the time a part failed or survived as of the analysis date. When the driving factor of reliability is usage rather than time, however, the analysis becomes more involved.
There are many applications in which failures are dependent upon usage, not time. For example, in the automotive industry, the failure behavior in the majority of the products is mileage-dependent rather than time-dependent. These kinds of products present a challenge for data analysis. For surviving units still working in the field, how do we know their usage (“life”) and how do we incorporate it into the estimation of the failure distribution?
Suppose that you have been collecting sales (units in service) and returns data. For the returns data, you can determine the number of failures and their usage (by reading the odometer value, for example). Determining the number of surviving units Arrow (suspensions)......
Я посмотрел книжки. По смыслу подходят: в теории вероятностей - "Дополнение", в математике - "Надстройка". Физический смысл: дополнение "Выборки" (Sample) до полной совокупности событий. Но что-то нет уверенности в такой трактовке, может кто более плотно сталкивался с этим понятием??
