Review of prognostic problem in condition-based maintenance

DESCRIPTION This paper empirically examines the relationship between the failure patterns observed in industry and the potential benefits to the introduction of a Condition-Based Maintenance (CBM) strategy. Industry appears to often misunderstand this relationship although for an informed decision the correct recording and analyses of failure data is important. Publicly available relevant data of wear are, at best, limited. A large number of academic and industrial papers are available which compare the efficiency of various maintenance strategies within a range of different industries. However, the conclusions clearly state that (1) they are large differences between various industrial sectors and (2) the relationship between data analyses and maintenance strategy development is, at best, limited. Wherever such data collection mechanisms are not in place, maintenance decisions rely mostly on intuition and expert views. This paper suggests the importance of further supporting such i...

The maintenance of a deteriorating system is often imperfect: the system after maintenance will not as good as new, but younger. Imperfect maintenance study indicates a significant breakthrough in reliability and maintenance theory. Research activities in maintenance engineering have been conducted over the past 30 years and more than 40 mathematical imperfect maintenance models have been proposed for estimating the reliability measures and determining the optimum maintenance policies. Various treatment methods and optimal policies on the imperfect maintenance are discussed and summarized in this paper. Several important results for imperfect maintenance are also presented.

2010

Unexpected system failures pose a significant problem in human safety and health care applications, service and manufacturing sectors, national infrastructure (nuclear power plants and civil structures), and national security (military operations). The main challenges associated with unexpected failures are related to characterizing the failure uncertainty and the stochastic nature of the degradation processes. An accurate failure time prediction and a reliability assessment are necessary if the appropriate maintenance resources (personnel, tools, spare parts, etc.) are to be assembled. For this reason the thesis presents a mathematical framework for integrating degradation-based sensor data streams with high-level logistical decision models. To achieve this goal, a software has been realized in order to simulate a discontinuous operational scenario (such as aircraft operations) in which two different maintenance policies were applied, a scheduled and a condition-based one. The former refers to a typical maintenance policy, in which no prognostic data are available, so that maintenance is scheduled basing only on prior knowledge of components' failure behavior. The latter approach, instead, implements the information given by prognostics in order to fully exploit the component's residual useful life and reduce the lead time to deliver spare parts. The last change is achieved through a revision and a modification of the entire supply chain model in a Just-In-Time-like perspective: thanks to a more precise knowledge of the time to failure, spare parts can be stored in depots so to be in the maintenance zone just before they are needed. Thus, it is possible to move these parts to higher level depots, where hold stocking costs are typically lower. As for prognostics, it has been made possible through the realisation of a RUL estimation algorithm. It is to say that many techniques have been found in literature, but none of them faced the prognostic problem with the aim of finding a closed form for RUL estimation The most promising predictive algorithm, among those developed before this work, turned out to be a Bayesian estimator based on the degradation pattern of the monitored component, under the likely assumption of exponential shape of such pattern. This algorithm has been the starting point for the one developed in this work. Leveraging on Bayesian probability theory, the up-to-date RUL probability density function of the component is evaluated at each time step, starting from the prior knowledge of the component's residual life, a stochastic parameter that is evaluated from experimental tests always done before commissioning. The ________________________________________________________________ information about RUL prediction was then used to define the optimal moment at which scheduling and performing maintenance. These values were found through an objective function optimization that took into account the main drivers associated to condition-based maintenance decision making process. Furthermore the opportunity to introduce CBM (condition based maintenance) concepts based on prognostic into a cracked railway axle management is investigated. The performances of two different prognostic algorithm are assessed on the basis of their RUL (remaining useful life) predictions accuracy. The CBM approach is compared to the classical preventive maintenance approach to railway axle maintenance management based on expensive and regular NDT. The effect of monitoring frequency and the monitoring infrastructure size error is assessed as well.

Journal of Intelligent Manufacturing, 2015

In manufacturing enterprises, maintenance is a significant contributor to the total company's cost. Condition based maintenance (CBM) relies on prognostic models and uses them to support maintenance decisions based on the predicted condition of equipment. Although prognostic-based decision support for CBM is not an extensively explored area, there exist methods which have been developed in order to deal with specific challenges such as the need to cope with real-time information, to predict the health state of equipment and to continuously update maintenance-related recommendations. The current work aims at providing a literature review for prognostic-based decision support methods for CBM. We analyse the literature in order to identify combinations of methods for prognostic-based decision support for CBM, propose a practical technique for selecting suitable combinations of methods and set the guidelines for future research.

John Wiley & Sons, Inc. eBooks, 2017

According to the standard EN 13306 (2001), maintenance can be defined as a "combination of all technical, administrative and managerial actions during the life cycle of an item intended to retain it in, or restore it to, a state in which it can perform the required function" [EN 01]. It also includes a set of actions of troubleshooting, repairing, controlling and verifying physical equipment, and it should contribute to the improvement of industrial processes. From the traditional viewpoint, the maintenance function guarantees dependability characteristics of equipment, in particular its availability. Therefore, globally it aims to understand the failure mechanisms and to act accordingly in order to ensure that the system (the good) can perform the function that it has been conceived for. However, the missions of the maintenance function are no longer limited to the implementation of means to ensure the "goods service". Different requirements in terms of quality, safety and costs have emerged, and the challenges and prerogatives of the maintenance function have evolved in the last 20 years. 1.1.1.2. Challenges and prerogatives of the maintenance function The challenges of the maintenance function can be discussed from different points of view. First of all, as industrial equipment becomes more and more complex, it requires greater competence in maintenance. Furthermore, the company evolves within a strongly competitive environment and the financial concerns are very prominent. Therefore, maintenance doesn't escape the cost reduction rule. At another level, for some years, the industrial managers have been facing more significant environmental and social constraints. It is not sufficient anymore to be content with

2010

Machinery health management is becoming increasingly important and the diagnosis of failures based on machinery condition has been analyzed in-depth in the last few decades, and is relatively well understood. However, prognostic evaluation of faults in a machine is a harder task that involves predicting impending faults in the system and determining remaining useful life of the machinery. A survey of algorithms, and a detailed description of a hybrid CBM prognostic techniques being investigated for use in ground vehicle systems will be presented. The system incorporates a number of techniques to process and analyze the current condition of a ground vehicle, and to generate a prognosis for each subsystem in the vehicle. The discussion will describe a means of testing, verifying and iteratively improving prognostic capabilities throughout the lifecycle of the platform. INTRODUCTION Vehicles generally have some form of diagnostic indicators and the ability to perform diagnostic tests a...

2015

This report focuses on condition-based and opportunity-based maintenance of equipment subject to failures and deterioration. These strategies of preventive maintenance attempt to avoid performing unnecessary maintenance task, by taking actions only if the equipment reached a certain level of deterioration, the threshold. A analytic approach was used to determine this level of deterioration for which the costs of maintenance actions during a long period of time are minimal. Minimizing the costs will lead to less downtime which will results in both lower costs for maintenance actions but also in more profit from the production. Several models were investigated by use of both simulation and analytic models. The probabilities on a breakdown and on opportunities for maintenance as well as the costs for maintenance are taken into account. When the probability on a maintenance opportunity becomes larger, the threshold can be set later. On the other hand, when the probability on a breakdown becomes larger, this threshold must be set earlier. The analytic model is general, so specific data is needed to give an optimal advice per situation. Situation-specific, adding planned maintenance after a certain amount of time will decrease the costs even more and an optimal time span exist for which the costs are reduced most.

Lecture Notes in Mechanical Engineering, 2013

Correlation between the quality degradation of a product and maintenance of a machine is often established by the production engineers. To asses this correlation, some assumptions are made. In most cases it is assumed that the quality of the product degrades after a fixed number of operation cycles of the production machine. Therefore maintenance of the production machine is only performed after this number of cycles is accomplished. This kind of assumptions is often not valid in modern industry since high variability of products, tolerances of machines / components, reliability variations of these components, extensive / smooth usage, etc. make this degradation quite dynamic in time. As a result, the quality of the product could get degraded in a fast way if this variability is high or in a slow way if this variability is low. Both cases will lead to low benefit because of lost production in the former case or redundant maintenance in the latter one. In this paper we propose a solution to this problem by maximizing the benefit using online monitoring of product's quality degradation and maintenance cost evolution. A Condition Based Maintenance framework for industry developed in Prognostics for Optimal Maintenance (POM) project [1] and described in [2] is applied to two industrial use cases in order to deploy and validate the proposed technique.

An effective condition based maintenance regime requires a good understanding of asset criticality; failure rates modes and, effects; as well as total cost of failures. Therefore, understanding what to monitor for a given asset requires reliability and financial related data.

2011

Many models and methodologies to predict the remaining useful life (RUL) of a component or system are investigated nowadays. However, decision making based on these predictions (RUL) is still an underexplored area in maintenance management. The objective of this paper is to quantify the added value of this prognostic information (RUL). This is done by constructing a stochastic discrete-event simulation model, which optimizes maintenance action scheduling, based on prognostic information on the different components. Cost and ...