Industry 4.0, cyber-physical systems, and digital twins are generating ever more data. This opens new opportunities for companies, as they can monitor development and production processes, improve their products, and offer additional services. However, companies are often overwhelmed by Big Data, as they cannot handle its volume, velocity, and variety. Additionally, they mostly do not follow a strategy in the collection and usage of data, which leads to unexploited business potentials. This paper presents the implementation of a Digital Twin module in an industrial case study, applying a concept for guiding companies on their way from data to value. A standardized use case template and a procedure model support the companies in (1) formulating a value proposition, (2) analyzing the current process, and (3) conceptualizing a target process. The presented use case entails an anomaly detection algorithm based on Gaussian processes to detect defective products in real-time for the extrusion process of aluminum profiles. The module was initially tested in a relevant environment; however, full implementation is still missing. Therefore, technology readiness level 6 (TRL6) was reached. Furthermore, the effect of the target process on production efficiency is evaluated, leading to significant cost reduction, energy savings, and quality improvements.

Gaussian processes (GPs) can be used to predict future states of a system with credible intervals when considering multiple previous trajectories for training. For example, predicting the degradation of mechanical structures is one application in which they have shown their usefulness. In modeling the system output as a GP, the output is presumed to be normally distributed—assuming the predictions to be defined from negative to positive infinity. However, this assumption does not hold in many applications as, for example, crack lengths and damage indices can only assume positive values. Moreover, several degradation trajectories for training are rare in real-world applications, and the current state of a monitored system, which is used to update the prediction, can often be not directly measured. This paper presents an approach that utilizes warped GPs for treating data that is not normally distributed while considering multiple degradation trajectories for training. The approach is successfully applied to two different crack propagation examples: first, an analytically computed pre-cracked infinite plate, and second, two equally manufactured aluminum structures that resemble a lower section of a wing. For the investigated aerospace structures, we use finite element (FE) simulations to generate multiple degradation trajectories for training. To estimate their hidden degradation states, we infer the current crack length from strain measurements by using Bayesian inference. The results show that the approach of warped GPs provides more accurate predictions than using standard ones for non-normally distributed data, as is the case for crack growth problems. The approach enables quick training of warped GPs while considering multiple training trajectories. Additionally, the crack lengths estimated from strain measurements agree well with the visually inspected ones. Ultimately, the presented approach enables estimating the current and future degradation states with credible intervals that can be used to improve maintenance scheduling.

Aircraft structures experience various kinds of loads over their entire lifetime, typically leading to fatigue, and ultimately structural failure. To avoid structural failure during operation, the ...

During the development of aerospace structures, typically many fatigue tests are conducted. During these tests, much effort is put into inspections in order to detect the onset of failure before complete failure. Strain sensor data may be used to reduce inspection effort. For this, a sufficient number of sensors need to be positioned appropriately to collect the relevant data. In order to minimize cost and effort associated with sensor positioning, the method proposed here aims at minimizing the number of necessary strain sensors while positioning them such that fatigue-induced damage can still be detected before complete failure. A suitable detection criterion is established as the relative change of strain amplitudes under cyclic loading. Then, the space of all possible crack lengths is explored. The regions where the detection criterion is satisfied before complete failure occurs are assembled into so-called detection zones. One sensor in this zone is sufficient to detect criticality. The applicability of the approach is demonstrated on a representative airplane structure that resembles a lower wing section. The method shows that four fatigue critical spots can be monitored using only one strain sensor in a non-intuitive position. Furthermore, we discuss two different strain measures for crack detection. The results of this paper can be used for reliable structural health monitoring using a minimum number of sensors.

Strain-based Structural Health Monitoring: Computing Regions for Critical Crack Detection