Prediction of system reliability using failure types of components based on Weibull lifetime distribution

Modern products are complicated and standards of reliability are higher than ever before. Therefore, prediction of system reliability is essential, especially as the time available for developing products has decreased. Most of the previous studies assumed that the causes of failure are random. That is, the failure rates of components follow exponential distributions. To reflect various types of failure such as initial, random, or wear-out failure, we developed a novel procedure for estimating system reliability based on the Weibull distribution. We analyzed the effect of component selection on the types of system failure. Finally, we verified the proposed method by analyzing warranty data on actual Korean products.

This paper discusses the problem of system reliability prediction by accelerated testing results on its components. This problem appears when the testing of a system as a whole either has high cost or may be impossible in a short period of time, especially at the beginning of development. A multi-variate Weibull model is proposed to utilize testing results of components in predicting system reliability with reduced test length and minimized cost. Prediction of system reliability in a given situation means that we must know how to calculate not only the point estimation of reliability index, but also the lower confidence bound (LCB) with given confidence probability q (q=0.8-0.95). In this case, the authors' goal is to give the algorithm for calculating not by approximation for LCB (based as a rule on normal distribution of point reliability estimation), but exact LCB corresponding to a given confidence probability.

This paper focuses on analysis and prediction of system reliability by using methods for achieving data-driven, customer focused reliability and availability assessment. The Markov models can be used to create system level architecture-based models that allow assessment of reliability and available parameter estimation on a system level. Analysis of finer granularity provides more insights on the root cause of problems from the customer view and future work also addressed how this can be made practical and useful.

Manufacturing systems are increasingly becoming automated and complex in nature. Highly reliable and flexible manufacturing systems (FMSs) are the necessity of manufacturing industries to fulfill the increasing customized demands. Worldwide, FMSs are used in industries to attain high productivity in production environments with rapidly and continuously changing manufactured goods structures and demands. Reliability prediction plays a very significant role in system design in the manufacturing industry, and two crucial issues in the prediction of system reliability are failures of equipment and system configuration. This novel work presents a stochastic model to analyze the performance of an FMS through its reliability characteristics, in the concern of its equipment. To improve the reliability of FMS, determine the sensitivity of the reliability measures of FMS. FMS consists of many components such as machine tools like CNC, automatic handling and material storage, controller and robot for serving load. The designed system is studied by using the Markov process, supplementary variable technique, Laplace transformation, coverage factor and Gumbel–Hougaard family copula to obtain various reliability measures. For some realistic approach, particular cases and graphical illustrations are also obtained.

In this work the analysis of interval-censored data, with Weibull distribution as the underlying lifetime distribution has been considered. It is assumed that censoring mechanism is independent and non-informative. As expected, the maximum likelihood estimators cannot be obtained in closed form. In our simulation experiments it is observed that the Newton-Raphson method may not converge many times. An expectation maximization algorithm has been suggested to compute the maximum likelihood estimators, and it converges almost all the times. The Bayes estimates of the unknown parameters under gamma priors are considered. If the shape parameter is known, the Bayes estimate of the scale parameter can be obtained in explicit form. When both the parameters are unknown, the Bayes estimators cannot be obtained in explicit form. Lindley’s approximation, importance sampling procedures and Metropolis Hastings algorithm are used to compute the Bayes estimates. Highest posterior density credible intervals of the unknown parameter are obtained using importance sampling technique. Small simulation experiments are conducted to investigate the finite sample performance of the proposed estimators, and the analysis of two data sets; one simulated and one real life, have been provided for illustrative purposes.

Today, numerous reliability prediction methods exist for electronic systems. A detailed literature survey is conducted to investigate the various techniques/models to ensure electronic components/system's reliability. Based on such a method's merits and limitations, we recommend using the hybrid model to predict an electronic system's reliability prediction in the distinct development phase of the product life cycle to get higher accuracy.

An approach to system reliability under wearout and overload failure is outlined, where conventional models for these mechanisms are used to define wear-dependent failure rates in terms of response “peak” statistics. System-failure rates are seen to be bounded above, making predictions based on the Weibull distribution too conservative at the “tail”, while certain normal-derived predictions are too optimistic. However, Weibull distributions are found quite useful in approximating the various response peak statistics for certain impulsive-noise environments encountered in random vibrations and elsewhere. The pitfalls of misusing “normalized” curves of reliability are cited and the need for future investigations is expressed.

The increasing use of computer numerical control (CNC) machines requires better prediction of the reliability of their servo control systems. A novel reliability prediction model based on radial basis function (RBF) neural network optimized by improved particle swarm optimization (IPSO) was proposed. It can overcome the disadvantages of conventional methods, which are time consuming and resource intensive. The major influences on the reliability of servo system include torque, temperature, current, and complexity. An improved algorithm for predicting the mean time between failure (MTBF) of servo systems based on a particle swarm optimization (PSO) and an RBF neural network algorithm is proposed. Two common problem of the PSO: local minimization and slow convergence were solved by the IPSO. “Zero failure” data preprocessing, data normalization, and small-sample data enhancement were performed on the original data. A homogenized sampling method is proposed to extract training and testing samples. Experimental results show that the improved PSO-based RBF neural network is superior to back propagation (BP) and RBF networks in terms of accuracy in servo system reliability prediction.

In order to ensure high reliability of complex engineered systems against deterioration or natural and man-made hazards, it is essential to have an efficient and accurate method for estimating the probability of system failure regardless of different system configurations (series, parallel, and mixed systems). Since system reliability prediction is of great importance in civil, aerospace, mechanical, and electrical engineering fields, its technical development will have an immediate and major impact on engineered system designs. To this end, this chapter presents a comprehensive review of advanced numerical methods for system reliability analysis under uncertainty. Offering excellent in-depth knowledge for readers, the chapter provides insights on the application of system reliability analysis methods to engineered systems and gives guidance on how we can predict system reliability for series, parallel, and mixed systems. Written for the professionals and researchers, the chapter is designed to awaken readers to the need and usefulness of advanced numerical methods for system reliability analysis.

Estimation of parameters from progressively censored data using EM algorithm

Forecasting systems reliability based on support vector regression with genetic algorithms

Simulation-based system reliability prediction may require significant computations, particularly when the expected value of the system failure probability is relatively low. A methodology is presented for variance reduction of sampling-based series system reliability predictions based on optimal allocation of Monte Carlo samples to the individual failure modes. An algorithm is presented for adaptively allocating samples to member failure modes based on initial estimates of the member failure probabilities pi. The methodology is demonstrated for a simple series system and a gas-turbine engine disk modeled using a zone-based series system approach. For the example considered, it is shown that the computational accuracy of the method does not appear to depend on the initial pi estimate. However, the computational efficiency is highly dependent on the initial pi estimate. The results can be applied to improve the efficiency of sampling-based series system reliability predictions.

High product quality and reliability are critical in the medical device industry. Accurate reliability prediction during the product development stage provides inputs for the design strategy and boosts understanding and confidence in product reliability before products are released to the market. A Bayesian framework provides a straightforward solution for product system reliability prediction with quantified uncertainty. This is achieved by propogating the uncertainty of model parameters, use conditions, and component-level reliability to the system level. In cases where a single data source is insufficient to accurately estimate reliability due to sample size limitations or potential biases, Bayesian methods are flexible to aggregate various sources of data to reduce uncertainty. In this work, Bayesian models are applied in the Design for Reliability process to assess medical device system reliability with confidence, where frequentist methods may be approximate or non-existent.

Offshore system safety and reliability considering microbial influenced multiple failure modes and their interdependencies

Analytical techniques for reliability and availability prediction of mesh-connected systems are proposed. The models are based on the submesh requirements. First, a reliability model is proposed assuming that a submesh can be always recognized if it exits. Analysis of the linear consecutive n-out-of-N system is extended using an expanding row/column technique to evaluate the submesh reliability. An alternative approach called row folding is also discussed. Due to the high complexity involved in computing the exact reliability, both of these techniques use approximation to estimate lower bounds. Next, the submesh reliability is computed based on two different allocation policies, known as the two-dimensional buddy system (TDBS), and the frame sliding (FS). The model with the TDBS is further extended to estimate the reliability of multiple working submeshes, which is useful in a multiuser environment. Availability analysis for a submesh of the required size is conducted using a Markov chain (MC). State truncation is used to reduce the computation time, and the MC is solved using a software package called HARP. Validation of the analytical models is done through extensive simulation. Issues, such as reliability comparison based on allocation policies, and methods for improving system reliability are addressed using the analytical models.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>