Quality Intelligence (QI)

德国政府提出的工业4.0计划专注于提高生产率的灵活制造系统。网络物理系统(CPS)是工业4.0的核心，也是其在生产和物流过程中的技术集成。CP是一个复杂的系统，拥有海量的可用数据。数据可以通过观察、测量和统计调查获得，并描述了生成知识的第一步。如果数据与特定的上下文相关联，就会生成信息。最后，知识源于将信息与经验、概念和专业知识联系起来。知识管理为从数据和信息中生成知识提供了基础。商务智能(Business Intelligence，BI)是应信息系统需求而产生的一种新方法。BI结合了集成、改进、转换和分析数据的所有活动。供应链是CPS的一种形式。在整个供应链中，产生了大量关于产品、订单、工艺和质量的数据。供应链管理已经意识到这些数据的重要性。存在几种侧重于供应链内数据交换的重要性的方法。除此之外，在供应链管理的目标系统中，产品、过程和系统质量的高影响是常见的。这两个方面之间的联系，即对整个供应链中与质量有关的数据进行分析，以支持质量管理的决策，仍然缺乏联系。学术空白应该在研究项目质量情报(QI)中填补。研究目标是开发一个供应链参考模型中与质量相关的不稳定性的预测模型。因此，在第一步中，应该开发供应链的与质量相关的描述模型。将识别、分配与质量有关的数据，并分析相互依赖关系。通过本体论的方法，将所获得的结果集成到预测模型中。研究结果应该能够为未来质量相关体系状况的研究提供依据。这项研究有助于有效利用现有数据等资源。由于对质量问题的事后反应，事前避免与质量相关的不稳定性可以降低质量成本。

The initiative Industry 4.0 from the german government focusses on flexible manufacturing systems with enhanced productivity. Cyber-Physical Systems (CPS) are the core of Industry 4.0 as well as for its technical integration in production and logistics processes. CPS are complex systems and a huge amount of available data. Data can be obtained by observations, measurements and statistical investigations and describes the first step of generating knowledge. If data get linked with a certain context, information is generated. Finally, knowledge originates by linking information with experiences, concepts and expertise. Knowledge Management provides the basics for the generation of knowledge form data and information. Business Intelligence (BI) has become a novel approach arising from the demand for informational systems. BI combines all activities of integrating, improving, transforming and analyzing data. Supply Chains are one form of CPS. Across a supply chain numerous data concerning products, orders, processes and quality are incurred. Supply chain management has realized the importance of these data. Several approaches focusing the importance of data exchange within supply chains exist. Beyond that, the high impact of product, process and system quality is common in the target system of supply chain management. A link between both aspects, that is an analysis of quality-related data across a supply chain for decision support of quality management, is still missing. The academic void should be picked up within the research project Quality Intelligence (QI). Research objective is the development of a prediction model for quality-related instabilities across a supply chain reference model. Therefore, in a first step a quality-related description model of a supply chain should be developed. The quality-related data will be identified, allocated and the interdependencies analyzed. By means of ontology, the gained results should be integrated into the prediction model. The research results should enable conclusions about quality-related system statuses in the future. This research contributes to efficient usage of resources such as existing data. The ex-ante avoidance of quality-related instabilities could cut quality costs due to ex-post reactions on quality problems.