Degradation mode and criticality analysis based on product usage data

Over the last decade, a rapid development of internet, wireless mobile telecommunication, and product identification technologies make whole product life cycle visible and controllable, which can improve several operational issues over the whole product life cycle: product design improvement, predictive maintenance, rational decision on end-of-life products, and so on. The key element to solve these issues is to assess the degradation status of a product based on gathered data during product usage period. However, despite its importance, due to the interrupted information flow of the product life cycle after product sales, it has not received enough attention in the literature until now. To overcome this limitation, this study develops a decision support method, called degradation mode and criticality analysis (DMCA), for the analysis of product degradation status based on gathered product usage data. The proposed method enables us to identify and assess the degradation status of a product and give a suitable guide for the next action. To show the effectiveness of the proposed approach, a case study for a heavy construction equipment vehicle is introduced.

Decision support methods for closed-loop conceptual design

Jongho Shin

The dissertation deals with closed-loop product lifecycle management (PLM) approaches for the product conceptual design improvement using gathered data during the usage period of a product. In closed-loop PLM, the data generated in each lifecycle phase can be shared in different lifecycle phases and used for various objectives such as design, maintenance, recycle, and so on. Among them, we focus on the information flow from the middle of life (MOL) phase to the beginning of life (BOL) phase. From the MOL phase, the product usage data is gathered and transferred to the BOL phase. The transferred data should be transformed into suitable information (e.g. contextualized usage data such as failure rate, mean time between failure, and etc.) and knowledge (e.g. design modification suggestions for product improvement) for the conceptual design activity of the BOL phase. This dissertation provides a procedure and related methods for the transformation of data into information and knowledge. For this, we develop a product usage data transformation method consisting of three steps: 1) evaluation of a used component/part status, 2) correlation between a used component/part status and design parameters, and 3) estimation of product improvement cost investment for possible modifications of required design parameters. In the first step of our method, we define an index value which indicates the degree of performance degradation of used components/parts functions considering the historical change of the performance degradation over time. In this index, the historical change of the performance degradation is considered as three characteristics: criticality, abnormality, and severity. In the second step of our method, we correlate the evaluated performance degradation of component/part function and the field data which consists of the working environment and operational setting during product operation. To this end, we follow several sub-steps. In these sub-steps, we use various methods such as a function structure model, a degradation scenario, a clustering technique, and a relation matrix. To analyze product functions and define degradation scenarios, we build and use a function structure model. The clustering technique is used to classify the field data by product status. The relation matrix is used to calculate the importance rate of the product functions and the product design parameters. The importance rate helps engineers to recognize which functions are critical in performance degradation and which design parameters are important from the viewpoint of the performance degradation. In the last step of our method, the found design parameters and their importance rates are used to estimate the cost investment for product design modification during the conceptual design phase. To do this, an extended house of quality (HOQ) is developed and a mixed integer non-linear programming (MINLP) formulation is proposed. To solve the problem of the cost investment estimation in a reasonable time, we provide three heuristic algorithms to solve the MINLP problem in a reasonable time. During the explanation of our method, we use two cases (turbocharger and locomotive) to show the validity of our method. From the application of our method into the case studies, we recognize critical design parameters (compressor wheel shape and the number of compressor wheel blades for turbocharger, and the diameter of brake cylinder for the locomotive) to be modified for the product improvement. An estimation of the required cost investment to modify these critical design parameters is calculated by the solution of the MINLP.

EPFL2009

Automated analysis of product related data generated from PLM ontology

Ana Milicic

In recent years, ontology for the Product Lifecycle Management domain has raised a lot of interest in research communities, both academic and industrial. It has emerged as a convenient method for supporting the concept of closed lifecycle information loop, which is one of the most important issues of PLM. By modeling relevant aspects collected from all lifecycle stages of a product, within one ontology, a common knowledge structure is created accessible to all actors. Assuming that appropriate mechanisms for updating ontology (or rather, instances that populate it) are provided, ontology becomes a base layer for a knowledge management platform. Useful experience and information from all productsâ life-cycle stages, can influence designerâs decisions and business strategies. The industrial research community has recognized this added value of ontological implementation, and there is an increasing number of developed ontologies for this purpose. Application of ontology contributes to time efficiency by reducing the time required to retrieve information. Furthermore, it allows for the enhancement of design decisions which are supported through additional information at the appropriate moment. Finally, ontology gives an overall perspective on a product's lifecycle, allowing from-the-top optimization. Different domains modeled in ontology, and software platforms that use them as a base layer, become interoperable and convenient to merge. The purpose of ontology as it is today is not to store data, for the most part because there are more efficient data base systems to handle large data amounts. Still, the domain modeled within ontology is composed of structured and un-structured data sets, and ontology itself can give us a top view on relations and dependences between these data sets. In this perspective, it holds a strong similarity to a relational data base, if relations in the data base where defined so that they depicted the real world in the most precise possible manner. In large companies today, handling a growing amount of data generated every day is becoming an increasingly relevant problem. Managing and storing them, although challenging, is still feasible, but holding data without understanding it carries little added value. In an effort to exploit useful information contained in unstructured data sources, a number of decision support systems and enterprise resource planning systems have been developed. They can be very diverse in functionality and efficiency but the one thing that they all have in common is that the user has to be the one making the initiative and defining the queries. This means that the user has to know which information he is looking for, or hoping to extract. As a consequence, the number of relevant correlations and dependencies between different factors of real life captured in the data are left unnoticed, simply because they were not assumed. In the PLM domain, this is particularly present since it involves a number of actors and most of them are interacting only with a small subset of domain concepts. Data mining as a discipline, gives a number of tools for resolving this issue. All of the algorithms are designed to detect correlations, underlying patterns or functions that generated the data. The problem of data mining techniques is that they are still performed mostly manually. Although deterministic steps of data mining procedures can be supported by existing software tools, the others remain an obstac

EPFL2015

Decision support methods for closed-loop conceptual design

Jongho Shin

EPFL2009

Automated analysis of product related data generated from PLM ontology

Ana Milicic

EPFL2015