In this paper we present a novel approach for data-driven Quality Management in industry processes that enables a multidimensional analysis of the anomalies that can appear and their real-time detection in the running system. The approach revolutionizes the way how quality control (and esp. anomaly detection) will be realized in production processes influenced by many parameters that can be in complex nonlinear correlations. It consists of two main steps: learning the normal behavior of the system (based on past data) and detecting an anomalous behavior in the real-time (by processing real-time data). The approach is especially suitable for modern industry systems that follow Industry 4.0 principles of ubiquity sensing and proactive responding. One of the main advantages is the self-adaptive nature of the approach due to its data-driven orientation, so that the model and parameters of the approach will be continuously updated to the dynamicity of data. The approach has been applied in the process of manufacturing microwave ovens (Whirlpool) and in this paper we present results for the data-driven quality control of one of the most critical parts — microwave oven fan. Due to the high speed of the rotation, every item has to be very precisely produced (according to the CAD model), which requires very strong quality control process

No abstract

Abstract-Anomaly detection is the process of discovering some anomalous behaviour in the real-time operation of a system. It is a difficult task, since in a general case (multivariate anomaly detection, an anomaly can be related to the behaviour of several parameters which are not necessarily behaving anomalously per se, but their (complex) relation is anomalous (not usual/normal). This implies the need for a very efficient modeling of the normal behavior in order to know what should be treated as anomalous/outlier/unusual. Consequently, classical model-driven approaches, due to their focusing on the selected parameters for creating models, are not able to model the behavior if the whole system. This is why data-driven approaches for anomaly detection are getting ever more important for the industry use cases where hundreds (thousands) of parameter should be taken into account. However, current approaches are usually focused on the univariate anomaly detection (or some variations of it), so without going into observing the entire space of relations (computation very difficult). In this paper we present a novel approach for the multivariate anomaly detection that is based on modeling and managing the streams of variations in a multidimensional space. The main advantage of this approach is the possibility to observe the relations between variations of a large set of parameters and create clusters of "normal/usual" variations. In order to ensure scaling, which is one of the most challenging requirements, the approach is based on the usage of the big data technologies for realizing data analytics tasks/calculations. The approach is realized as a part of D2Lab (Data Diagnostics Laboratory) framework and has been applied in several industrial use cases. In this paper we present a very interesting usage for the anomaly detection in the process of functional testing of home appliances devices (in particular case refrigerators) after manufacturing/assembling process. It has been done for a bug vendor (Whirlpool), who expects huge saving in testing and improved customer satisfaction from this approach.

No abstract