Soumaya Yacout

Optimal condition based maintenance with imperfect information and the proportional hazards model

Condition based maintenance (CBM) is based on collecting observations over time, in order to assess equipments state, to prevent its failure and to determine the optimal maintenance strategies. In this paper, we derive an optimal CBM replacement policy when the state of equipment is unknown but can be estimated based on observed condition. We use a proportional hazards model (PHM) to represent the systems degradation. Since equipments state is unknown, the optimization of the optimal maintenance policy is formulated as a partially observed Markov decision process (POMDP), and the problem is solved using dynamic programming. Practical advantages of combining the PHM with the POMDP are shown.

Fault diagnosis in power transformers using multi-class logical analysis of data

This paper presents the implementation of a novel multi-class diagnostic technique for the detection and identification of faults based on an approach called logical analysis of data (LAD). LAD is a data mining, artificial intelligence approach that is based on pattern recognition. In the context of condition based maintenance (CBM), historical data containing condition indices and the state of the machine are the inputs to LAD. After training and testing phases, LAD generates patterns that characterize the faulty states according to the type of fault, and differentiate between these states and the normal state. These patterns are found by solving a mixed 0–1 integer linear programming problem. They are then used to detect and to identify a future unknown state of equipment. The diagnostic technique has already been tested on several known machine learning datasets. The results proved that the performance of this technique is comparable to other conventional approaches, such as neural network and support vector machine, with the added advantage of the clear interpretability of the generated patterns, which are rules characterizing the faults’ types. To demonstrate its merit in fault diagnosis, the technique is used in the detection and identification of faults in power transformers using dissolved gas analysis data. The paper reaches the conclusion that the multi-class LAD based fault detection and identification is a promising diagnostic approach in CBM.

Diagnosis of rotor bearings using logical analysis of data

Purpose – The purpose of this paper is to test the applicability and the performance of an approach called logical analysis of data (LAD) on the detection of faults in rotating machinery using vibration signals.Design/methodology/approach – LAD is a supervised learning data mining technique that relies on finding patterns in a binary database to generate decision functions. The hypothesis is that a LAD‐based decision model can be used as an effective tool for automatic detection of faults in rolling element bearings. A novel Multiple Integer Linear Programming approach is used to generate patterns for the LAD decision model. Frequency and time‐based features are extracted from rotor bearing vibration signals and are pre‐processed to be suitable for use with LAD.Findings – The results show good classification accuracy with both time and frequency features.Practical implications – The diagnostic tool implemented in the form of software in a production or operations maintenance environment can be very helpfu...

LAD-CBM; new data processing tool for diagnosis and prognosis in condition-based maintenance

This paper investigates the application of a data mining technique called Logical Analysis of Data (LAD) to condition-based maintenance. The existing classification techniques are mainly based on statistical analysis and modeling approaches. This paper presents a classification technique based on combinatory and Boolean theory. It is shown that LAD is particularly suitable for detecting the state of equipment because of its new way of pre-processing noisy and missing data. A numerical example and an application are presented.

Concurrent optimization of the design and manufacturing stages of product development

The problem of concurrent optimization of the design and the process planning stages when a new product is developed is addressed. The paper advocates for a simultaneous approach rather than the traditional sequential one. A mathematical representation of this approach is given for these two stages. A mathematical programming technique is used to find the optimal values of the design and the process characteristics. The objective function is a quality loss function. The constraints are the customer requirements, the products specification limits, the parts’ dimensional limits and the process capability. The traditional sequential approach of concurrent engineering is compared with the proposed simultaneous approach. A parametric analysis of the objective function is performed by applying an interactive multi-objective goal programming technique. A numerical example of a low-pass electrical circuit is given. It is shown that the proposed approach leads to better efficient solutions than the sequential approach. The decision-maker interacts with the optimization process and can choose the efficient solution that best satisfies the companys needs.

Rogue components: their effect and control using logical analysis of data

There is a small subset of any repairable component population that can develop a failure mode outside the scope of the standard repair and overhaul procedures, which makes them “rogue”. When this happens, a Darwinian-like “natural selection” phenomenon ensures that they will be placed in the most disadvantageous position in the asset management program, negatively affecting multiple aspects of the operational and maintenance organizations. Rogue components have long plagued the airline industry and created havoc in their asset management programs. In this paper, we describe how these rogues develop, outline the natural selection process that leads to their hampering the asset management program, and examine some of the negative impacts that ensue. Then we propose a Condition based maintenance approach to control the development of these components. We explore the use of a supervised learning data mining technique called Logical analysis of data (LAD) in CBM for the purpose of detecting rogues within a population of repairable components. We apply the resulting LAD based decision model on an inventory of turbo compressors belonging to an airline fleet. Finally, we evaluate the applicability of LAD to the rogue component detection problem and review its efficiency as a decision model for this type of problem.

Fault detection and diagnosis for condition based maintenance using the Logical Analysis of data

Presently, most maintenance decisions are mainly based on failure event. Nevertheless, in many cases and for many types of equipment this event can rarely be seen or can happen after many years of utilization. In these cases, maintenance decisions are based on fault diagnostics. This paper presents an artificial intelligent approach to fault detection and diagnosis. This approach is called Logical Analysis of data, and it is based on a combinatorics, Boolean, and optimization theory. Its main power stems from the fact that it detects logical patterns that can be easily interpreted. These patterns are used in the classification of observations collected by condition monitoring, and thus in the diagnosis of faults. An application is presented. Analysis of the results obtained shows high classification accuracy and useful features for detection and analysis.

Concurrent optimization of customer requirements and the design of a new product

This paper proposes a mathematical programming technique to optimize the product development process. Using a concurrent engineering approach, the paper presents a formulation that maps the different stages of product development. The decision variables of these stages are then determined simultaneously. While the Quality Function Deployment Technique (QFD) is based on a qualitative sequential approach, this paper proposes a holistic quantitative approach to concurrent product-process optimization. The mathematical programming technique is applied to the first two stages of product development: the optimization of customer satisfaction and the products design.

Remaining useful life prediction using prognostic methodology based on logical analysis of data and Kaplan---Meier estimation

Most of the reported prognostic techniques use a small number of condition indicators and/or use a thresholding strategies in order to predict the remaining useful life (RUL). In this paper, we propose a reliability-based prognostic methodology that uses condition monitoring (CM) data which can deal with any number of condition indicators, without selecting the most significant ones, as many methods propose. Moreover, it does not depend on any thresholding strategies provided by the maintenance experts to separate normal and abnormal values of condition indicators. The proposed prognostic methodology uses both the age and CM data as inputs to estimate the RUL. The key idea behind this methodology is that, it uses Kaplan–Meier as a time-driven estimation technique, and logical analysis of data as an event-driven diagnostic technique to reflect the effect of the operating conditions on the age of the monitored equipment. The performance of the estimated RUL is measured in terms of the difference between the predicted and the actual RUL of the monitored equipment. A comparison between the proposed methodology and one of the common RUL prediction technique; Cox proportional hazard model, is given in this paper. A common dataset in the field of prognostics is employed to evaluate the proposed methodology.

Assessment of quality activities using Taguchi's loss function

Abstract Quality control, quality assurance and total quality management are all concerned with managing and controlling variations. The less variation a system has the better quality it provides. Using the Taylor Expansion Series, Dr. Taguchi (1986) developed a mathematical model in which loss is a quadratic function of the deviation of the quality of interest from its target value. Based on this concept, sound management decisions can be made regarding the true worth of quality improvement efforts. In this article, we compare four quality policies: a “do-nothing” policy, an appraisal policy, a prevention policy and a mix of prevention and appraisal policies. The costs associated with each policy are modelled using Taguchis loss function. To account for the dynamic nature of these costs, the policies are compared over a period of time.