Volume 89, Issue 4 - Qualität smarter Mess- und Sensorsysteme / Gastherausgeber: Klaus-Dieter Sommer, Michael Heizmann, Andreas Schütze

In this paper we describe how the digital transformation (i. e., the adoption of digital technology) of society affects National Metrology Institutes like VSL. The presented ideas represent the personal viewpoint of the author, who works at the Dutch national metrology institute VSL. They don’t necessarily correspond to the vision of VSL as institute. This digital transformation has many different aspects of social, economic and technical nature. In this paper we will mainly focus on some mathematical and statistical aspects which are important for modelling measurement instruments and analyzing measurement data. We will discuss how modern techniques like artificial intelligence, digital twins, digital calibration certificates and the introduction of the new definition of the SI system of units affect national metrology institutes. Important changes are the usage of complex algorithms and models in measurement instruments, as well as the introduction of novel calibration approaches and the digitalization of the services provided by NMIs.

Nowadays machine learning methods and data-driven models have been used widely in different fields including computer vision, biomedicine, and condition monitoring. However, these models show performance degradation when meeting real-life situations. Domain or dataset shift or out-of-distribution (OOD) prediction is mentioned as the reason for this problem. Especially in industrial condition monitoring, it is not clear when we should be concerned about domain shift and which methods are more robust against this problem. In this paper prediction results are compared for a conventional machine learning workflow based on feature extraction, selection, and classification/regression (FESC/R) and deep neural networks on two publicly available industrial datasets. We show that it is possible to visualize the possible shift in domain using feature extraction and principal component analysis. Also, experimental competition shows that the cross-domain validated results of FESC/R are comparable to the reported state-of-the-art methods. Finally, we show that the results for simple randomly selected validation sets do not correctly represent the model performance in real-world applications.

The increasing amount of available process data from machining and other manufacturing processes together with machine learning methods provide new possibilities for quality control and condition monitoring. A prediction of the workpiece quality in an early machining stage can be used to alter current quality control strategies and could lead to savings in terms of time, cost and resources. However, most methods are tested under controlled lab conditions and few implementations in real manufacturing processes have been reported yet. The main reason for this slow uptake of this promising technology is the need to prove the capability of a machine learning method for quality prediction before it can be applied in serial production and supplement current quality control methods. This article introduces and compares approaches from the fields of machine learning and quality management in order to assess predictions. The comparison and adaption of the two approaches is carried out for an industrial use case at Bosch Rexroth AG where the diameter and the roundness of bores are predicted with machine learning based on process data.

Cognitive sensor systems (CSS) determine the future of inspection and monitoring systems for the nondestructive evaluation (NDE) of material states and their properties and key enabler of NDE 4.0 activities. CSS generate a complete NDE 4.0 data and information ecosystem, i. e. they are part of the materials data space and they are integrated in the concepts of Industry 4.0 (I4.0). Thus, they are elements of the Industrial Internet of Things (IIoT) and of the required interfaces. Applied Artificial Intelligence (AI) is a key element for the development of cognitive NDE 4.0 sensor systems. On the one side, AI can be embedded in the sensor’s microelectronics (e. g. neuromorphic hardware architectures) and on the other side, applied AI is essential for software modules in order to produce end-user-information by fusing multi-mode sensor data and measurements. Besides of applied AI, trusted AI also plays an important role in CSS, as it is able to provide reliable and trustworthy data evaluation decisions for the end user. For this recently rapidly growing demand of performant and reliable CSS, specific requirements have to be fulfilled for validation and qualification of their correct function. The concept for quality assurance of NDE 4.0 sensor and inspection systems has to cover all of the functional sub-systems, i. e. data acquisition, data processing, data evaluation and data transfer, etc. Approaches to these objectives are presented in this paper after giving an overview on the most important elements of CSS for NDE 4.0 applications. Reliable and safe microelectronics is a further issue in the qualification process for CSS.

Artificial neural networks are used in various fields including spectral unmixing, which is used to determine the proportions of substances involved in a mixture, and achieve promising results. This is especially true if there is a non-linear relationship between the spectra of mixtures and the spectra of the substances involved (pure spectra). To achieve sufficient results, neural networks need lots of representative training data. We present a method that extends existing training data for spectral unmixing consisting of spectra of mixtures by learning the mixing characteristic using an artificial neural network. Spectral variability is considered by random inputs. The network structure used is a generative adversarial net that takes the dependence on the abundances of pure substances into account by an additional term in its objective function, which is minimized during training. After training further data for abundance vectors for which there is no real measurement data in the original training dataset can be generated. A neural network trained with the augmented training dataset shows better performance in spectral unmixing compared to being trained with the original dataset. The presented network structure improves already existing results obtained with a generative convolutional neural network, which is superior to model-based approaches.

Automated vehicles rely on a precise intrinsic and extrinsic calibration of all sensors. An exact calibration leads to accurate localization and object detection results. Especially for sensor data fusion, the transformation between different sensor frames must be well known. Moreover, modular and redundant platforms require a large number of sensors to cover their full surroundings. This makes the calibration process complex and challenging. In this article, we describe the procedure to calibrate the full sensor setup of a modular autonomous driving platform, consisting of camera, lidar, and radar sensors, in four subsequent steps. At first, the intrinsic and extrinsic camera parameters are determined. Afterwards, the transformation from lidar to camera on the one hand and from lidar to radar on the other hand is estimated. Lastly, the extrinsic calibration between all lidars and the vehicle frame is performed. In our evaluation, we show that these steps lead to an accurate calibration of the complete vehicle.