Access Restriction

Author Al-Garni, Ahmed Z. ♦ Jamal, Ahmad ♦ Saeed, Farooq ♦ Kassem, Ayman H.
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Failure Rate Analysis ♦ Neural Network ♦ Brake Employing Neural Network ♦ Failure Rate ♦ Brake Assembly ♦ Log-sigmoid Function Integer ♦ Regression Xd Input ♦ Artificial Neural Network Whereas ♦ Xd Xk Activation Level ♦ K-1 Integer ♦ Observation Number ♦ Actual Data ♦ Weibull Regression Model ♦ Straight Line Number ♦ Weibull Model ♦ Minimum Guaranteed Life ♦ Neural Network O ♦ Matrix Independent Variable ♦ Neural Network Slope ♦ Artificial Neural Network ♦ Model Building ♦ Aviation Maintenance Facility ♦ Nomenclature Y-intercept Integer ♦ Planning Horizon ♦ Neural Network Number ♦ One-layered Feed-forward Back-propagation Algorithm ♦ Material Requirement Planning System ♦ Commercial Airplane
Abstract The failure rate analysis of brake assemblies of a commercial airplane, i.e., Boeing 737, is analyzed using the artificial neural network and Weibull regression models. One-layered feed-forward back-propagation algorithm for artificial neural network whereas three parameters model for Weibull are used for the analysis. Three years of data are used for model building and validation. The results show that the failure rate predicted by neural network is closer in agreement with the actual data than the failure rate predicted by the Weibull model. Results also indicate that neural network can be effectively integrated into an aviation maintenance facility computerized material requirement planning system to forecast the number of brake assemblies needed for a given planning horizon. Nomenclature c = y-intercept d = integer, 1 ≤ d ≤ m F(t) = failure rate at time t f(net) = log-sigmoid function i = integer, 0 ≤ i ≤ N’ j = integer, 1 ≤ j ≤ k-1 k = integer, m ≤ k ≤ N+n k ’ = number, 0.65 < k ’ < 1 l = number of landings m = number of inputs to the neural network m ’ = slope of a straight line N = number of neurons in neural network N ’ = number of observations n = number of outputs to the neural network Os = outputs from the neural network, s varies from 1 to n O(t) = Os(t) R(t) = reliability, 1-F(t) T(t) = time beyond a given time, T> t t = flight operational time ti = flight operational time, at the observation tmin = minimum time t tr = cumulative contact time on the runway to = minimum guaranteed life of the brake assembly W = weight matrix x = independent variable in regression Xd = input to the neural network, d varies from 1 to m xj = normalized Xd xk = activation level of the neurons
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study