The Problem of Sprinkler Reliability Sprinkleri patikimumo problema

Sprinkler systems allow a considerable reduction of fire risk in buildings. Unfortunately, sprinklers are not fail-safe technical systems. Relatively high rates of sprinkler failures evoke the problem of reliability. A solution to this problem is considered from several viewpoints. The diversity of sprinklers' failure modes is the first challenge for estimating reliability (failure probability). It is found that the use of the available data for estimation is problematic. The second challenge is that the published data is insufficiently described to allow a verification of its relevance to the specific case of failure probability estimation. It is suggested to apply the published data with partial relevance to Bayesian inference about failure probabilities. The data is used for developing prior distributions of the unknown values of the probabilities. Bayesian inference is carried out on the basis of binomial distribution used to model the operation of sprinklers on demand basis. A problem of aging and a possible increase in failure probability in the course of sprinkler service is shortly discussed. Article in English Nagrin ta sprinkleri sistem patikimumo vertinimo problema. Patikimumo matu laikoma sprinkleri atsako tikimyb . Rasta, kad ios tikimyb s vertinimas yra s lygi kai sud tingas u davinys. Sprinkleriai gali patirti atsak labai vairiais būdais. Be to, is atsakas patiriamas retai. Tai lemia duomen apie sprinkleri ne sijungimo gaisro metu negausum , neleid ia vertinti atsako tikimyb s, remiantis klasikiniu santykinio da nio po iūriu. Patikimumo vertinim komplikuoja tai, kad duomenys apie sprinkleri atsakus renkami gana nesistemingai, be teorinio pagrindo ir standartizavimo alies, regiono ar pasaulio mastu. Duomenys paprastai fiksuojami pasyviai, kai sprinkleriai ne sijungia gaisro metu. Turimi empiriniai sprinkleri atsako da niai gali būti naudojami kaip iurk tūs tikimybi ver iai. Juos galima taikyti Bajeso analizei, kai reikia formuoti apriorin atsako tikimyb s tank . tank galima atnaujinti pasitelkiant negausius duomenis, surinktus konkre ioje alyje, ir gautus stebint konkretaus tipo sprinklerius. Teorinis modelis kuriuo galima nusakyti sprinkleri atsak tik tinum per pasirinkt gaisr skai i , yra binominis skirstinys. Sprinkleri atsako tikimyb s vertinim galima atlikti taikant standartin binominio skirstinio parametro vertinimo procedūr Bajeso statistikos metodais. Pagrindin binominio skirstinio prielaida yra ta, kad sprinkleriai nesensta ir j atsako tikimyb nesikei ia laikui b gant. Galima sp sti, kad i priel