Classical Reliability Theory Research Articles

Reliability of Self-Driving Cars: When Can We Remove the Safety Driver?

Self-driving cars and other vehicles are being increasingly demonstrated, released, and deployed on roads. Yet only a handful of special-case vehicles have obtained a permit to go fully driverless, and our passenger cars still require drivers at the steering wheel to correct the car if something goes wrong. Safety drivers, which operate autonomous vehicles in testing phases, upon occasions were unable to correct the faulty behavior of their vehicles, inducing accidents and, unfortunately, casualties. This article proposes a method to analyze the reliability of autonomous vehicles applying the classical reliability theory and software reliability growth models (SRGMs). This method is then applied to real-world data to get some predictions on what is really needed to safely remove the driver and go fully driverless.

Application of Generator-Electric Motor System for Emergency Propulsion of a Vessel in the Event of Loss of the Full Serviceability of the Diesel Main Engine

Oil tanker disasters have been a cause of major environmental disasters, with multi-generational impacts. One of the greatest hazards is damage to the propulsion system that causes the ship to turn sideways to a wave and lose stability, which in storm conditions usually leads to capsizing and sinking Despite the perceived consequences of maritime disasters in the current solutions for the propulsion of oil tankers, there are no legal or real solutions for independent emergency main propulsion in this type of ship. Stressing that the reliability of the propulsion system has a significant impact on the ship’s safety at sea, the authors presented a new solution in the form of a power take-off/power take-in (PTO/PTI) system. This is the emergency use of a shaft generator as the main electric motor, operating in parallel in a situation when the main engine (ME), (the main engine of the ship’s direct high-power propulsion system that is slow-speed) loses the operational capability to propel the ship. Since one cause of wear, or failure, of the main engines is improper operational decisions, the paper shows the wear mechanism in relation to the accuracy of operational decisions. Using classical reliability theory, it also shows that the use of the proposed system results in an increase in the reliability of the propulsion system. The main topic of the paper was the use of an electrical system called PTO/PTI as an emergency propulsion system on the largest commercial vessels, such as bulk carriers and crude oil tankers, which has not been used before in maritime technical solutions. Semi-Markov processes, continuous in time, discrete in states, and which are used in technology, were also proposed as a tool describing the process of the operation of such a ship propulsion system, and they are useful to support operational decisions affecting the state of the technical condition of the engine. There are two ship operation strategies that can be adopted: the four-state model, for normal operation, and the three-state model, which operates with the occurrence of failure. For these types of models, their limiting distributions were defined in the form of probabilities. It was also demonstrated that faster than expected engine wear and the occurrence of inoperability of the main engine can be caused by wrong operational decisions made by the shipowner or crew. Using this type of main engine operating methodology, it is possible to support the decision of the engineer to stop the main engine and to subject it to the process of restoration to an acceptable state of technical condition (before the failure or during the failure in severe storm conditions), with the parallel use of the proposed electric propulsion (PTO/PTI) as an emergency propulsion, giving the crew a chance to maintain the steering necessary to maintain safe lateral stability.

Анализ надежности узлов подвижного состава на основе эксплуатационных данных

Objective: To determine the most failure-prone rolling stock components and assemblies by processing statistical data obtained during operation using the classical reliability theory; to develop recommendations for maintaining the operational state of individual rolling stock components. Methods: Methods for calculating the quantitative reliability characteristics are used based on the rolling stock operational statistical data. Results: The 5-year operational data have been used to provide tabulated statistics on the failure rate of various rolling stock equipment. Reliability indicators have been calculated for various types of rolling stock equipment and the corresponding graphs have been plotted. Based on the calculations, the recommendations for the rolling stock maintenance have been developed. Practical importance: The calculations and the recommendations described determine the types of rolling stock equipment requiring more attention during maintenance

Method for integrating classical and network reliability: A time varying network reliability evaluation

AbstractMany capacitated flow network papers treat reliability as a time‐invariant property. However, network components degrade over time suggesting that methods to quantify the time‐varying reliability of a network are appropriate. This paper proposes a method to compute the reliability of a multistate capacitated flow network in terms of multistate components characterized by a life distribution. The approach enables the calculation of the probability that demand can be satisfied over period of time despite component degradation. Examples are provided to clarify the steps required and to illustrate the assessments enabled. Based on the classical reliability theory, the Weibull reliability function is employed to characterize the degradation of network components. However, the approach is general and other distributions are also possible. The results indicate that the approach can assist a network supervisor determine reasonable demand rate and time constraint to satisfy demand as well as reason about alternative reliability improvement strategies.

Structural fuzzy reliability analysis using the classical reliability theory

This study is focused on a novel approach for calculating structural fuzzy reliability by using the classical reliability theory. In order to handle the structural fuzzy reliability problem, the formulae for establishing normal random variables equivalent to symmetric triangular fuzzy number are presented. From these equivalent random ones, the original problem is converted to the basic structural reliability problems, then the methods of the classical reliability theory should be applied to calculate. Moreover, this study proposes two notions in terms of central fuzzy reliability and standard deviation of fuzzy reliability as well as a calculation procedure to define them. Lastly, the ultimate fuzzy reliability of the proposed method is established and utilized to compare the allowable reliability in the design codes. Numerical results are supervised to verify the accuracy of the proposed method.

Calculation of building structures and features of its automation technology

Recently, the issues of evaluating the quality of building structures and predicting their reliability are becoming increasinglyimportant, especially for the construction of industrial facilities of the old fund. Powerful mathematical methods are beingdeveloped to evaluate the performance of structures and predict their reliability, but there are no automated computer systemsfor such analysis. At present, programs for the determined calculation of structures have been developed, which implementmethods for the resistance of materials, theoretical and construction mechanics, but they do not provide an opportunity to determineand predict reliability, especially objects of the old fund. The methods of the classical reliability theory combinedwith the methods of statistical modeling are used in the work, which requires the use of modern IT technologies methodswith the development of appropriate software systems

A Multistate Model of Reliability of Farming Machinery

The article describes a multistate model of reliability of farming machinery as a deductive stochastic model of the process of changes in the technical conditions observed during operation. These conditions determine the capacity of machinery to fulfil functions, simultaneously keeping safety and maintaining acceptable costs of possible repairs. The theory of semi-Markov processes was used to solve the problem. After detailed analysis of the symptoms of damage to exemplary groups of farming machinery (rotary mowers, rotary harrows and harvesting presses) we obligatorily and arbitrarily proposed an optimal four-state reliability model to describe changes in technical conditions. In contrast to the classic reliability theory, which allows only two states of technical usability (either a machine is fit to function or not), we also allowed intermediate states, because not all types of damage affect the functionality of machinery. This approach increases the probability of technical usability of machinery and rationally delays the moment of premature repair.

Uncertainty theory as a basis for belief reliability

Belief reliability is a newly developed, model-based reliability metric which considers both what we know (expressed as reliability models) and what we don’t know (expressed as epistemic uncertainty in the reliability models) about the reliability. In this paper, we show that due to the explicit representation of epistemic uncertainty, belief reliability should not be regarded as a probability measure; rather, it should be treated as an uncertain measure in uncertainty theory. A minimal cut set-based method is developed to calculate the belief reliability of coherent systems. A numerical algorithm is, then, presented for belief reliability analysis based on fault tree models. The results of application show that the developed methods require less computations than the structure function-based method of classical reliability theory.

Research on Connection and Function Reliability of the Oil＆Gas Pipeline System

Pipeline transportation is the optimal way for energy delivery in terms of safety, efficiency and environmental protection. Because of the complexity of pipeline external system including geological hazards, social and cultural influence, it is a great challenge to operate the pipeline safely and reliable. Therefore, the pipeline reliability becomes an important issue. Based on the classical reliability theory, the analysis of pipeline system is carried out, then the reliability model of the pipeline system is built, and the calculation is addressed thereafter. Further the connection and function reliability model is applied to a practical active pipeline system, with the use of the proposed methodology of the pipeline system; the connection reliability and function reliability are obtained. This paper firstly presented to considerate the connection and function reliability separately and obtain significant contribution to establish the mathematical reliability model of pipeline system, hence provide fundamental groundwork for the pipeline reliability research in the future.

Reliability Evaluation for Clustered WSNs under Malware Propagation.

We consider a clustered wireless sensor network (WSN) under epidemic-malware propagation conditions and solve the problem of how to evaluate its reliability so as to ensure efficient, continuous, and dependable transmission of sensed data from sensor nodes to the sink. Facing the contradiction between malware intention and continuous-time Markov chain (CTMC) randomness, we introduce a strategic game that can predict malware infection in order to model a successful infection as a CTMC state transition. Next, we devise a novel measure to compute the Mean Time to Failure (MTTF) of a sensor node, which represents the reliability of a sensor node continuously performing tasks such as sensing, transmitting, and fusing data. Since clustered WSNs can be regarded as parallel-serial-parallel systems, the reliability of a clustered WSN can be evaluated via classical reliability theory. Numerical results show the influence of parameters such as the true positive rate and the false positive rate on a sensor node’s MTTF. Furthermore, we validate the method of reliability evaluation for a clustered WSN according to the number of sensor nodes in a cluster, the number of clusters in a route, and the number of routes in the WSN.

A new fault tree analysis approach based on imprecise reliability model

Fault tree analysis is a powerful and computationally efficient technique for safety analysis and reliability prediction. It decomposes an undesired failure into multiple possible root causes by constructing a sub-event tree and spreading it into basic events. Classical reliability theory using probability theory to quantify the uncertainties of basic events encounters many challenges when failure data are limited. In this case, uncertainty quantification should be carried out based on subjective information, such as experts’ assessment or engineers’ experience. As a generalization of probability theory, imprecise probability theory can quantify subjective information as the upper and lower expectations or previsions. In this article, a fault tree analysis algorithm incorporating subjective information into imprecise reliability models of basic events is proposed to calculate the failure interval of lubricating oil warning system.

Generalizability theory for the perplexed: A practical introduction and guide: AMEE Guide No. 68

Background: Generalizability theory (G theory) is a statistical method to analyze the results of psychometric tests, such as tests of performance like the Objective Structured Clinical Examination, written or computer-based knowledge tests, rating scales, or self-assessment and personality tests. It is a generalization of classical reliability theory, which examines the relative contribution of the primary variable of interest, the performance of subjects, compared to error variance. In G theory, various sources of error contributing to the inaccuracy of measurement are explored. G theory is a valuable tool in judging the methodological quality of an assessment method and improving its precision.Aim: Starting from basic statistical principles, we gradually develop and explain the method. We introduce tools to perform generalizability analysis, and illustrate the use of generalizability analysis with a series of common, practical examples in educational practice.Conclusion: We realize that statistics and mathematics can be either boring or fearsome to many physicians and educators, yet we believe that some foundations are necessary for a better understanding of generalizability analysis. Consequently, we have tried, wherever possible, to keep the use of equations to a minimum and to use a conversational and slightly “off-serious” style.

Survivability evaluation towards attacked WSNs based on stochastic game and continuous-time Markov chain

Because a large number of Wireless Sensor Networks (WSNs) are deployed in unsafe surroundings, the survivability evaluation towards attacked WSNs has become a critical issue. Due to its popularity, the cluster-based structure of WSNs in this paper is selected to be studied and regarded as a serial-parallel system according to its characteristics. In order to set up the relation between the intention of attack behaviors and the randomness of continuous-time Markov chain (CTMC), we construct an attack-prediction stochastic game that is able to attain the attack probabilities adopted by the attacker in different states. Therefore, the consequence from a successful attack can be modeled as a deliberate state change of the CTMC. Upon this, the state transition matrix describing various states during the lifetime of an attacked sensor node can be formed. We are then able to compute the MTTF (Mean Time To Failure) of an attacked sensor node in perspective of CTMC. Based on the classical reliability theory, we thus propose a mechanism of survivability evaluation for attacked WSNs, which is composed of the reliability, survival lifetime, and availability in the steady state. Our experiments show the influence degree of the game parameters to the expected motivation of the attacker as well as disclose the relation between the MTTF of an attacked sensor node and the expected motivation of the attacker. In addition, the effectiveness of our survivability evaluation metrics is validated. These results will be able to build up the theoretical foundation to guide the design of highly survival WSNs.

Revisiting Measurement Models in Psychosomatic Medicine Research

In this article, we describe how a latent variable modeling approach to the specification of measurement error unifies and benefits traditional methods of examining reliability in psychology and medicine. The models presented include classical reliability and generalizability theory to account for measurement error, latent class analysis to assess sensitivity and specificity, and item response theory to improve questionnaire development. We also illustrate how working with latent variables, in addition to addressing measurement error, may help deal with some instances of missing data. Throughout the article, analyses and results from examples and published articles are presented to illustrate the advantage of working with latent variables.

A Failure Detection and Prediction Mechanism for Enhancing Dependability of Data Centers

 Abstract—Modern data centers continue to grow in their scale and complexity. They are changing dynamically as well due to the addition and removal of system components, changing execution environments, frequent updates and upgrades, online repairs and more. Classical reliability theory and conventional methods do rarely consider the actual state of a system and are therefore not capable to reflect the dynamics of runtime systems and failure processes. In this paper, we present an unsupervised failure detection and prediction method using an ensemble of Bayesian models. It characterizes normal execution states of the system and detects anomalous behaviors. We implement a prototype of our failure detection and prediction mechanism and evaluate its performance on a data center test platform. Experimental results show that our proposed method can forecast failure dynamics with high accuracy.

Stable unstable reliability theory

Classical reliability theory assumes that individuals have identical true scores on both testing occasions, a condition described as stable. If some individuals' true scores are different on different testing occasions, described as unstable, the estimated reliability can be misleading. A model called stable unstable reliability theory (SURT) frames stability or instability as an empirically testable question. SURT assumes a mixed population of stable and unstable individuals in unknown proportions, with w(i) the probability that individual i is stable. w(i) becomes i's test score weight which is used to form a weighted correlation coefficient r(w) which is reliability under SURT. If all w(i) = 1 then r(w) is the classical reliability coefficient; thus classical theory is a special case of SURT. Typically r(w) is larger than the conventional reliability r, and confidence intervals on true scores are typically shorter than conventional intervals. r(w) is computed with routines in a publicly available R package.

SHORT‐TERM TRAINING AND ASSESSMENT FOR PERFORMANCE OF A SENSORY DESCRIPTIVE PANEL FOR THE OLFACTOMETRIC ANALYSIS OF AROMA EXTRACTS

ABSTRACT A study on the performances of a panel on the ability to discriminate between odor notes characteristic to nectarine fruits of different maturity (from unripe to fully ripe) was carried out by computing, from analysis of variance results of standardized scores, the agreement coefficient, which describes variation of ratings for a single product, and the reliability coefficient, which reflects discrimination ability of a panel for a group of products. Panelists, after short‐term training for recognition of the main odor attributes of peach aroma, scored the odor profile of both model solutions and Spring Bright nectarine aroma extracts from pool of fruit having well‐defined maturation degrees. Panel performances were good in terms of both agreement and reliability for the descriptors related to unripeness (sharp, herbaceous) while were good for agreement but fair for reliability for descriptors related to ripeness (fruity, ripe). PRACTICAL APPLICATIONSThe use of agreement and reliability coefficient, which are based on classical reliability theory and recent advances in psychological measurement, is quite a novel technique in evaluating performances of sensory panels. In this study, these coefficients were applied to monitor and compare performances of both the whole panel in evaluating attributes and the single panelist in evaluating each attribute. The results of the study underlined the usefulness of the graphical presentation of the two indices on the rating quality space in comparing individual panelist performances. In this way the selection of panelists according to their ability in rating a distinctive feature of a product can be easily accomplished.

Probabilistic interval reliability of structural systems

The probabilistic reliability approach is the most widely used method for reliability analysis. The recent research shows that the reliabilities of structural systems strongly depend on the parameters of the probability model. It is possible that the little error in the estimation of the parameters may lead to the remarkable error of the resulting probability. In this study, we introduce the interval approach into the conventional reliability theory. We present a novel approach which allows us to obtain the system failure probability interval from the statistical parameter intervals of the basic variables. This approach is a combination of the two techniques, namely the classical reliability theory and the interval analysis. In the end of this paper, we show the feasibility of the proposed approach through two examples of the truss systems.

On qualitative and operational reliability of electronic brake systems for heavy duty vehicles

The development of the safety critical systems of future commercial vehicles is mainly driven by the social demand, that the societies want to see safer, more reliable vehicles on the roads, which can also handle more complex situations than human driver can. It is questioned whether the approaches of the classical reliability theory are appropriate for redundant electronic systems, especially if they have a safety-critical nature, such as the electronic brake system, which has been used in commercial vehicles in Europe for almost a decade.

Viability in chemical engineering systems

Reliability (viability) in chemical engineering plant is considered. It is shown that classical reliability theory does not fully correspond to the reliability of such systems and that the viability of industrial technologies is determined also by the characteristics of the chemical and phase transformations.