Christoph Gröger

Supporting manufacturing design by analytics, continuous collaborative process improvement enabled by the advanced manufacturing analytics platform

The manufacturing industry is faced with global competition making efficient, effective and continuously improved manufacturing processes a critical success factor. Yet, media discontinuities, the use of isolated analysis methods on local data sets as well as missing means for sharing analysis results cause a collaborative gap in Manufacturing Process Management that prohibits continuous process improvement. To address this challenge, this paper proposes the Advanced Manufacturing Analytics (AdMA) Platform that bridges the gap by integrating operational and process manufacturing data, defining a repository for analysis results and providing indication-based and pattern-based optimization techniques. Both the conceptual architecture underlying the platform as well as its current implementation are presented in this paper.

The mobile manufacturing dashboard

Real-time monitoring and analysis of manufacturing processes are critical success factors in the smart factory. While there is a variety of data analytics tools for process optimization, almost each of these applications is designed for desktop PCs and focuses on selected process aspects, only. I. e., there is a gap between the site the analysis outcomes occur (the management level) and the site where an immediate reaction to these results is required (the factory shop floor). Even worse, there is no mobile, holistic and analytics-based information provisioning tool for workers and production supervisors on the shop floor but rudimentary systems designed for limited application areas, only. Therefore, we introduce our Mobile Manufacturing Dashboard (MMD), a situation-aware manufacturing dashboard for mobile devices. The MMD provides advanced analytics and addresses the full range of process-oriented information needs of both shop floor workers and production supervisors. In this paper, we give a brief overview of the MMDs major architecture and implementation aspects and describe two representative real-world scenarios for the MMD. These characteristic scenarios target shop floor workers and production supervisors and illustrate situation-aware information provisioning in the smart factory.

Prescriptive Analytics for Recommendation-Based Business Process Optimization

Continuously improved business processes are a central success factor for companies. Yet, existing data analytics do not fully exploit the data generated during process execution. Particularly, they miss prescriptive techniques to transform analysis results into improvement actions. In this paper, we present the data-mining-driven concept of recommendation-based business process optimization on top of a holistic process warehouse. It prescriptively generates action recommendations during process execution to avoid a predicted metric deviation. We discuss data mining techniques and data structures for real-time prediction and recommendation generation and present a proof of concept based on a prototypical implementation in manufacturing.

Warehousing manufacturing data: a holistic process warehouse for advanced manufacturing analytics

Strong competition in the manufacturing industry makes efficient and effective manufacturing processes a critical success factor. However, existing warehousing and analytics approaches in manufacturing are coined by substantial shortcomings, significantly preventing comprehensive process improvement. Especially, they miss a holistic data base integrating operational and process data, e. g., from Manufacturing Execution and Enterprise Resource Planning systems. To address this challenge, we introduce the Manufacturing Warehouse, a concept for a holistic manufacturing-specific process warehouse as central part of the overall Advanced Manufacturing Analytics Platform. We define a manufacturing process meta model and deduce a universal warehouse model. In addition, we develop a procedure for its instantiation and the integration of concrete source data. Finally, we describe a first proof of concept based on a prototypical implementation.

The Data-driven Factory - Leveraging Big Industrial Data for Agile, Learning and Human-centric Manufacturing

Global competition in the manufacturing industry is characterized by ever shorter product life cycles, increasing complexity and a turbulent environment. High product quality, continuously improved processes as well as changeable organizational structures constitute central success factors for manufacturing companies. With the rise of the internet of things and Industrie 4.0, the increasing use of cyber-physical systems as well as the digitalization of manufacturing operations lead to massive amounts of heterogeneous industrial data across the product life cycle. In order to leverage these big industrial data for competitive advantages, we present the concept of the data-driven factory. The data-driven factory enables agile, learning and human-centric manufacturing and makes use of a novel IT architecture, the Stuttgart IT Architecture for Manufacturing (SITAM), overcoming the insufficiencies of the traditional information pyramid of manufacturing. We introduce the SITAM architecture and discuss its conceptual components with respect to service-oriented integration, advanced analytics and mobile information provisioning in manufacturing. Moreover, for evaluation purposes, we present a prototypical implementation of the SITAM architecture as well as a real-world application scenario from the automotive industry to demonstrate the benefits of the data-driven factory.

The Deep Data Warehouse: Link-Based Integration and Enrichment of Warehouse Data and Unstructured Content

Data warehouses are at the core of enterprise IT and enable the efficient storage and analysis of structured data. Besides, unstructured content, e.g., emails and documents, constitutes more than half of the entire enterprise data and contains a lot of implicit knowledge about warehouse entities. Thus, holistic ana-lytics require the integration of structured warehouse data and unstructured content to generate novel insights. These insights can also be used to enrich the integrated data and to create a new basis for further analytics. Existing integration approaches only support a limited range of analytical applications and require the costly adaptation of the warehouse schema. In this paper, we present the Deep Data Warehouse (DeepDWH), a novel type of data warehouse based on the flexible integration and enrichment of warehouse data and unstructured content, addressing the variety challenge of Big Data. It relies on information-rich in-stance-level links between warehouse elements and content items, which are represented in a graph-oriented structure. Neither adaptations of the existing warehouse nor the design of an overall federated schema are required. We design a conceptual linking model and develop a logical schema for links based on a property graph. As a proof of concept, we present a prototypical imple-mentation of the DeepDWH including a link store based on a graph database.

ValueApping: An Analysis Method to Identify Value-Adding Mobile Enterprise Apps in Business Processes

Mobile enterprise apps provide novel possibilities for the optimization and redesign of business processes, e.g., by the elimination of paper-based data acquisitioning or ubiquitous access to up-to-date information. To leverage these business potentials, a critical success factor is the identification and evaluation of value-adding MEAs based on an analysis of the business process. For this purpose, we present ValueApping, a systematic analysis method to identify usage scenarios for value-adding mobile enterprise apps in business processes and to analyze their business benefits. We describe the different analysis steps and corresponding analysis artifacts of ValueApping and discuss the results of a case-oriented evaluation in the automotive industry.

A mobile dashboard for analytics-based information provisioning on the shop floor

Today’s turbulent global environment requires agility and flexibility of manufacturing companies to stay competitive. Thus, employees have to monitor their performance continuously and react quickly to turbulences which demands real-time information provisioning across all hierarchy levels. However, existing manufacturing IT systems, for example, manufacturing execution systems (MES), do hardly address information needs of individual employees on the shop floor. Besides, they do not exploit advanced analytics to generate novel insights for process optimisation. To address these issues, the operational process dashboard for manufacturing (OPDM) is presented, a mobile data-mining-based dashboard for workers and supervisors on the shop floor. It enables proactive optimisation by providing analytical information anywhere and anytime in the factory. In this paper, first, user groups and conceptual dashboard services are defined. Then, IT design issues of a mobile shop floor application on top of the advanced manufacturing analytics platform are investigated in order to realise the OPDM. This comprises the evaluation of different types of mobile devices, the development of an appropriate context model and the investigation of security issues. Finally, an evaluation in an automotive industry case is presented using a prototype in order to demonstrate the benefits of the OPDM for data-driven process improvement and agility in manufacturing.

The Stuttgart IT Architecture for Manufacturing

The global conditions for manufacturing are rapidly changing towards shorter product life cycles, more complexity and more turbulence. The manufacturing industry must meet the demands of this shifting environment and the increased global competition by ensuring high product quality, continuous improvement of processes and increasingly flexible organization. Technological developments towards smart manufacturing create big industrial data which needs to be leveraged for competitive advantages. We present a novel IT architecture for data-driven manufacturing, the Stuttgart IT Architecture for Manufacturing (SITAM). It addresses the weaknesses of traditional manufacturing IT by providing IT systems integration, holistic data analytics and mobile information provisioning. The SITAM surpasses competing reference architectures for smart manufacturing because it has a strong focus on analytics and mobile integration of human workers into the smart production environment and because it includes concrete recommendations for technologies to implement it, thus filling a granularity gap between conceptual and case-based architectures. To illustrate the benefits of the SITAM’s prototypical implementation, we present an application scenario for value-added services in the automotive industry.

Improving Business Processes Through Mobile Apps

Mobile apps offer new possibilities to improve business processes. However, the introduction of mobile apps is typically carried out from a technology point of view. Hence, process improvement from a business point of view is not guaranteed. There is a methodological lack for a holistic analysis of business processes regarding mobile technology. For this purpose, we present an analysis framework, which comprises a systematic methodology to identify value-added usage scenarios of mobile technology in business processes with a special focus on mobile apps. The framework is based on multi-criteria analysis and portfolio analysis techniques and it is evaluated in a case-oriented investigation in the automotive industry.