Susanne Dienst

Necessity of using Dynamic Bayesian Networks for feedback analysis into product development

Transformations into the modern business world is sustained by enhancement and improvement of strategies, systems and techniques towards evaluating and applying customer knowledge for the integration of Product Use Information (PUI) into product development, and meeting customer and market demands. In this paper the processing and modelling of PUI of many instances of one product type which is captured during the product use phase, e.g. condition monitoring data, failures or incidences of maintenance, raised by different graphical methods on the basis of a praxis and application scenario. Product Lifecycle Management (PLM) ensures a uniform data basis for supporting numerous engineering and economic organizational processes along the entire product life cycle - from the first product idea to disposal or recycling of the product. The processing and modelling of PUI raised by graphical methods like Bayesian Networks (BNs) or Dynamic Bayesian Networks (DBNs). In accordance, the product use knowledge leads back of the product development phase. This is used for discovering room for product improvements for the next product generation. Therefore the PUI of the different instances should be aggregated by applying fusion techniques to deduce/achieve generalized product improvements for a product type which is related to prospective research by focus on quality management systems and defining measures for customer satisfaction. As a result the significant aspect of this paper is to identify which graphical solution brings optimally the best results for the requirements of processing and modeling of PUI.

Development of a knowledge-based feedback assistance system of product use information for product improvement

Due to technological advancement, an increase in creating and storing digital data can be observed today, for instance throughout the product life cycle. Through especially product use, a large number of data are created. The data are mainly used during the product use phase (e.g. condition-based maintenance). However, those data can be used as feedback to generate knowledge and support the product developer through improving future product generations. This paper presents development and prototypical realisation of a feedback assistance system for the management, analysis and visualisation of feedback data. The system supports a product developer by improving the process of decision-making to discover development potentials. Thereupon, four modules have been developed to analyse related indicators statistically and to diagnose machine failures. The obtained knowledge about the current condition of machines should then be deployed to improve the next machine generations utilising the modules for decision support and prediction.

Concept for improving industrial goods via contextual knowledge provision

At present, product lifecycle data is provided, used, and archived only for very specific purposes. Textual data generated in product use can be very comprehensive and contain valuable information beyond its original purpose, e.g. for product development or improvement. This kind of information, however, is not fed back systematically, as its evaluation is currently not possible due to a lack of suitable methods and tools in product development. The paper in hand presents a concept designed to support product developers by introducing maintenance, service, and customer data, which has undergone restructuring into textual form in the product use phase, into product development. To process the restructured textual data, customized text mining methods are generated as a part of knowledge management in product development. These methods aim at identifying products, product generations, and failure descriptions, as well as the relationships among them. The knowledge gained through text mining is visualized in the work environment familiar to the product developer, and implements utilitarian visualization methods. Visualization is integrated into existing IT systems and provides knowledge required for product improvement or development in a target-oriented way. This extension to knowledge-based product development facilitates more efficient improvement of current and future products.

A conceptual data management model of a feedback assistance system to support product improvement

This paper describes a unifying data management concept for feedback assistance systems. The assistance system is to be integrated into existing system scenery. During the use of a hydraulic system, objective feedback such as sensor data or service data is captured and managed in local databases by the machine operators. The aim is to lead such Product Use Information (PUI) back into product development. That way, the product developer uses the information to derive additional and innovative potential to improve next generation products. The information flow is related in various systems i.e. the operator of the machine and the manufacturer. Furthermore, the PUI is managed inside the assistance system based on a data warehouse. The data warehouse is coupled with a Product Lifecycle Management (PLM) system, a well-known system to product developers. Within the PLM system, product master data is created and managed. This also serves as the basis for the assistance system, so that the data models for both systems have to be amalgamated.

Using data analysis for discovering improvement potentials in production process

Today technical product documentation and also related product use phase feedback contain valuable information about the companys products. In addition processing of various types of feedback provides opportunities for improvement potentials in product development especially in the next product generation and for increasing customer satisfaction. In this context, the acquired information is the key source of procedural knowledge particularly in product life cycle/data management. In the previous publications [1], [2] various knowledge based methods/functions like Bayesian Network, Dynamic Bayesian Network and Aggregation are presented, based on a kind of Assistance System for integration of product use information into product development. This paper presents a data integration approach through establishing an Assistance System for steel industry applications particularly for moderating of heat treatment process. In addition, a concept for using indicator systems for evaluating the performance of the Assistance System and particularly information quality is presented.

Use Case of Providing Decision Support for Product Developers in Product Improvement Processes

Industrial goods like pumps, engines, and gears are subject of cyclical improvements. An important input for such product updates is information from the use phase, especially information about failures that occurred during the use of current products. In a current research project the authors have developed a concept and a prototype for a Feedback Assistant System. The first realized modules of this assistant provide filtered and condensed product use information to the product developer. The paper in hands presents an extended concept and use case to assist the product developer in choosing the most suitable alternative in product improvement processes. The decisions are based on hard facts using diverse criteria.

NeuroCare—Personalization and Adaptation of Digital Training Programs for Mild Cognitive Impairments

Changes of cognitive and physical skills are a fundamental aspect of normal aging, but these personal skills fundamentally influence the quality of life and independency of a person. This is even more critical when the changes are decreasing in an above-average or even a pathologic manner. Keeping an individual’s cognitive skills at a certain level is therefore an individual as well as a societal goal. Accompanying the demographic change, however, the number of people with Mild Cognitive Impairments (MCI) rapidly increases. One intervention approach for the stabilization of the personal skill level and a deferment of possible further degradation are specialized cognitive and physical training programs. In order to increase the effectiveness and efficiency of such training programs, concepts for the adaption and personalization of such systems constitute the focus of the scientific discussion. In this publication, a new approach for the realization of digital dementia screening as well as technological solutions for the creation of adaptive and personalized training systems are presented. These approaches and solutions build the basis for the scientifically founded creation of effective and user-centered cognitive training modules within the research project NeuroCare, funded by the German Federal Ministry of Education and Research.