Search

Ultrasonic Testing (UT) has seen increasing application of machine learning (ML) in recent years, promoting higher-level automation and decision-making in flaw detection and classification. Building a generalized training dataset to apply ML in non-destructive evaluation (NDE), and thus UT, is exceptionally difficult since data on pristine and representative flawed specimens are needed. Yet, in most UT test cases flawed specimen data is inherently rare making data coverage the leading problem when applying ML. Common data augmentation (DA) strategies offer limited solutions as they don't increase the dataset variance, which can lead to overfitting of the training data. The virtual defect method and the recent application of generative adversarial neural networks (GANs) in UT are sophisticated DA methods targeting to solve this problem. On the other hand, well-established research in modeling ultrasonic wave propagations allows for the generation of synthetic UT training data. In this context, we present a first thematic review to summarize the progress of the last decades on synthetic and augmented UT training data in NDE. Additionally, an overview of methods for synthetic UT data generation and augmentation is presented. Among numerical methods such as finite element, finite difference, and elastodynamic finite integration methods, semi-analytical methods such as general point source synthesis, superposition of Gaussian beams, and the pencil method as well as other UT modeling software are presented and discussed. Likewise, existing DA methods for one- and multidimensional UT data, feature space augmentation, and GANs for augmentation are presented and discussed. The paper closes with an in-detail discussion of the advantages and limitations of existing methods for both synthetic UT training data generation and DA of UT data to aid the decision-making of the reader for the application to specific test cases.

Künstliche Intelligenz (KI) verspricht, Grenzen menschlicher Entscheidungsrationalität zu überwinden. Die aktuell wichtigste Form von KI sind künstliche neuronale Netze (KNN). Sie scheinen der Schlüssel für die Bewältigung und Nutzbarmachung jener Datenmengen zu sein, die mit der ubiquitären Digitalisierung einhergehen. Zugleich stellt die baubedingte Black-Box-Konstruktion von KNN ein zentrales Problem für die Wende hin zu digitalen Kulturen dar: Die Entscheidungen von KNN sind für Menschen notwendigerweise uninterpretierbar. Die derzeit beginnende Entwicklung von Systemen künstlicher Intelligenz, die KI überwachen und ihre Ergebnisse für den Menschen nachvollziehbar machen, ist daher zentral für den Gewinn von Kontrolle über die neuen technischen Systeme. Medienwissenschaftliche Expertise kann zu dieser Entwicklung beitragen. Der Blick in die Technikgeschichte legt außerdem nahe, dass entsprechende Lösungen in einen Kontext von Organisationsbildung und technischer Standardisierung eingebettet sein müssen, der die soziale Akzeptanz der neuen Technologie und der sie verwendenden Organisationen erhöht., Artificial intelligence (AI) promises to overcome limits of human rationality in decision-making. The currently most important form of AI consists of artificial neural networks (ANN). These appear to be the key for dealing with and making use of the deluge of data that ubiquitous digitalization has brought about. At the same time, the inbuilt black-box characteristics of ANN pose a major problem for the shift towards digital cultures. The decisions of ANN are inherently uninterpretable to humans. The incipient development of systems of artificial intelligence that monitor AI and render their results comprehensible to humans is therefore essential for control gains regarding the new technological systems. Expertise from media studies can contribute to this development. The history of technology furthermore suggests that solutions need to be embedded in a context of organization and technological standardization that increases the social acceptability of the new technology and the organizations using it.

We investigated and compared various algorithms in machine learning for anomaly assessment with different feature analyses on ultrasonic signals recorded by sensor networks. The following methods were used and compared in anomaly detection modeling: hidden Markov models (HMM), support vector machines (SVM), isolation forest (IF), and reconstruction autoencoders (AEC). They were trained exclusively on sensor signals of the intact state of structures commonly used in various industries, like aerospace and automotive. The signals obtained on artificially introduced damage states were used for performance evaluation. Anomaly assessment was evaluated and compared using various classifiers and feature analysis methods. We introduced novel methodologies for two processes. The first was the dataset preparation with anomalies. The second was the detection and damage severity assessment utilizing the intact object state exclusively. The experiments proved that robust anomaly detection is practically feasible. We were able to train accurate classifiers which had a considerable safety margin. Precise quantitative analysis of damage severity will also be possible when calibration data become available during exploitation or by using expert knowledge.

Due to the energy transition and the growth of electromobility, the demand for lithium-ion batteries has increased in recent years. Great demands are being placed on the quality of battery cells and their electrochemical properties. Therefore, the understanding of interactions between products and processes and the implementation of quality management measures are essential factors that requires inline capable process monitoring. In battery cell lamination processes, a typical problem source of quality issues can be seen in missing or misaligned components (anodes, cathodes and separators). An automatic detection of missing or misaligned components, however, has not been established thus far. In this study, acoustic measurements to detect components in battery cell lamination were applied. Although the use of acoustic measurement methods for process monitoring has already proven its usefulness in various fields of application, it has not yet been applied to battery cell production. While laminating battery electrodes and separators, acoustic emissions were recorded. Signal analysis and machine learning techniques were used to acoustically distinguish the individual components that have been processed. This way, the detection of components with a balanced accuracy of up to 83% was possible, proving the feasibility of the concept as an inline capable monitoring system.

Machine learning (ML) methods and algorithms have been applied recently with great success in quality control and predictive maintenance. Its goal to build new and/or leverage existing algorithms to learn from training data and give accurate predictions, or to find patterns, particularly with new and unseen similar data, fits perfectly to Non-Destructive Evaluation. The advantages of ML in NDE are obvious in such tasks as pattern recognition in acoustic signals or automated processing of images from X-ray, Ultrasonics or optical methods. Fraunhofer IKTS is using machine learning algorithms in acoustic signal analysis. The approach had been applied to such a variety of tasks in quality assessment. The principal approach is based on acoustic signal processing with a primary and secondary analysis step followed by a cognitive system to create model data. Already in the second analysis steps unsupervised learning algorithms as principal component analysis are used to simplify data structures. In the cognitive part of the software further unsupervised and supervised learning algorithms will be trained. Later the sensor signals from unknown samples can be recognized and classified automatically by the algorithms trained before. Recently the IKTS team was able to transfer the software for signal processing and pattern recognition to a small printed circuit board (PCB). Still, algorithms will be trained on an ordinary PC; however, trained algorithms run on the Digital Signal Processor and the FPGA chip. The identical approach will be used for pattern recognition in image analysis of OCT pictures. Some key requirements have to be fulfilled, however. A sufficiently large set of training data, a high signal-to-noise ratio, and an optimized and exact fixation of components are required. The automated testing can be done subsequently by the machine. By integrating the test data of many components along the value chain further optimization including lifetime and durability prediction based on big data becomes possible, even if components are used in different versions or configurations. This is the promise behind German Industry 4.0.

We developed a hardware-based cognitive user interface to help inexperienced and little technology-affine people to get easy access to smart home devices. The interface is able to interact (via speech, gestures, or touchscreen) with the user. By learning from the user’s behavior, it can adapt to each individual. In contrast to most commercial products, our solution keeps all data required for operation internally and is connected to other UCUI devices only via an encrypted wireless network. By design, no data ever leave the system to file servers of third-party service providers. In this way, we ensure the privacy protection of the user.

We present a miniaturized universal hardware module for acoustic pattern recognition in various types of multichannel sensor signals. The module implements configurable signal analysis (signal transforms, filter banks, statistical transforms) and a GMM-HMM recognizer. The main hardware components are a XC7A75T FPGA performing almost all the computations, a TMS320C6746 digital signal processor organizing the data flow and executing the automata search (decoding), 3×1 Gibit DDR2 memory and 4 Gibit flash memory. The module can be plugged into a host device and be connected to signal acquisition hardware. It can process input signals with up to approx. 250 kHz bandwidth for continuous input and up to approx. 3 MHz for burst input.

Diabetes is a widespread disease. Patients have to pay attention to their blood sugar value all the time. Hypoglycemia and hyperglycemia are dangerous and must be treated. Self-testing, typically involving a prick with a lancet, is often painful and the costs for testing devices and supplies are immense. It is well-known that the human voice carries all kinds of information and depends on various factors. Therefore we conjectured that it may also be influenced by the blood sugar level. This paper presents a preliminary study which shows that a patient's blood sugar condition actually seems to manifest itself in the voice. Results encourage us to go the next steps: a largescale long time study in collaboration with medical experts and, finally, the development of a measurement device or smartphone app.

In this paper we propose a universal strategy for the automatic interpretation of sensor signals. We focus on acoustic signals. However, any time series may be used. We assume that changes in an object's state cause a typical and reproducible change in the characteristics of the acquired sensor signal. In such cases we can train pattern recognizers basing on Hidden-Markov-Models or Support Vector Machines with data recordings of different object states and use these classifiers to assess the state of identical or similar objects. Our approach assumes that the sensor signals consist of elementary signal events and some kind of syntax defining their temporal relation (much like a musical score defines the temporal relation between notes). It is capable of automatically determining both, the elementary events and their syntax from the training data. We present experimental results from seven different applications from the fields of non-destructive testing, bio and music signal processing.

Multisensor problems are important tasks in the field of structural health monitoring. By means of signals originating from different sensors, we have to make a decision about the test object. We describe a universal, largely problem independent method, which applies statistical classifiers in order to identify objects or assess their state. This work presents the results of a series of studies, which systematically investigated such approaches for a great variety of technical and biological signals. We give an overview on the theoretical background and describe two selected application examples.

In this preliminary study we investigate the application of statistical classifiers for structural health monitoring of materials commonly used in airplanes. Our approach is based on the propagation of ultrasonic guided waves through materials like aluminum or carbon fiber reinforced plastic (CFRP). When the material gets damaged, the sound propagation changes. There are two ways of detecting these changes: we can use a physical model of the wave propagation or we can use a statistical approach. In this paper we focus on the latter. We present results using classifiers based on Hidden Markov Models (HMM) and Support Vector Machines (SVM). We compare these results to acoustic travel time tomography as a representative of the physical model based methods.

Decision making and classification methods are very important in the field of structural health monitoring and life cycle prediction. We want to introduce an approach basing on sequence classifiers which can be used to several applications without any explicit knowledge of structures. To illustrate the concept we explain the method by means of a special example. So we can demonstrate our approach detailed, but although not too abstract.

This paper reports on a study of applying an HMM-based labeler along with a tailored feature extraction to Korotkoff sounds. These sounds can be heard through a stethoscope during the auscultatory blood pressure measurement usually done at medical practices. While this method works well when the patient is at rest, interfering noise from muscles and joints cause major problems when the subject is doing any activities like sports or fitness exercises. We propose a signal processing and classification method to overcome these difficulties and present first promising results.

Non-speech acoustic signals are widely used as the input of systems for non-destructive testing. In this rapidly growing field, the signals have an increasing complexity leading to the fact that powerful models are required. Methods like DTW and HMM, which are established in speech recognition, have been successfully used but are not sufficient in all cases. We propose the application of generalized structured Markov graphs (SMG). We describe a task independent structure learning technique which automatically adapts the models to the structure of the test signals. We demonstrate that our solution outperforms hand-tuned HMM structures in terms of class discrimination by two case studies using data from real applications.