Automatic detection and prediction of discontinuities in laser beam butt welding utilizing deep learning. - In: Journal of advanced joining processes, ISSN 2666-3309, Bd. 6 (2022), 100119, S. 1-11
Laser beam butt welding of thin sheets of high-alloy steel can be really challenging due to the formation of joint gaps, affecting weld seam quality. Industrial approaches rely on massive clamping systems to limit joint gap formation. However, those systems have to be adapted for each individually component geometry, making them very cost-intensive and leading to a limited flexibility. In contrast, jigless welding can be a high flexible alternative to substitute conventionally used clamping systems. Based on the collaboration of different actuators, motions systems or robots, the approach allows an almost free workpiece positioning. As a result, jigless welding gives the possibility for influencing the formation of the joint gap by realizing an active position control. However, the realization of an active position control requires an early and reliable error prediction to counteract the formation of joint gaps during laser beam welding. This paper proposes different approaches to predict the formation of joint gaps and gap induced weld discontinuities in terms of lack of fusion based on optical and tactile sensor data. Our approach achieves 97.4 % accuracy for video-based weld discontinuity detection and a mean absolute error of 0.02 mm to predict the formation of joint gaps based on tactile length measurements by using inductive probes.
https://doi.org/10.1016/j.jajp.2022.100119
A data driven coordination between load balancing and interference cancellation. - In: Network and service management in the era of cloudification, softwarization and artificial intelligence, (2022), insges. 6 S.
Having multiple optimization functions in a mobile network brings demanding challenges in terms of coordination of potentially conflicting objectives. Typically each function aims at optimizing specific utilities modifying parameters that are coupled to other functions, which jeopardizes the stability of the system, specially if the policies followed by each function are dissonant. There are two commonly accepted approaches for Self-organized networks Function (SF) coordination: on the one hand side, there are heading (tailing) orchestration techniques in which a priori (posteriori) individual parameter conciliation takes place. On the other hand, it is possible address the conflict among SFs using global algorithms and optimize the network performance as a whole in a centralized manner. In this study, we aim at a solution of the second kind, interleaving the dynamic of two well-known SFs, namely Mobility Load Balancing (MLB) and Inter-Cell Interference Cancellation (ICIC), into one global technique and optimizing the global network performance using a method that combines fixed point algorithms and machine learning.
https://doi.org/10.1109/NOMS54207.2022.9789773
Decentralized machine learning based network data analytics for cognitive management of mobile communication networks. - In: Network and service management in the era of cloudification, softwarization and artificial intelligence, (2022), insges. 9 S.
The importance of network data analytics using advanced Machine Learning (ML) algorithms has been very well realized by the Telco industry and has resulted in the introduction of a dedicated Network Data Analytics Function (NWDAF) in the 5G service-based architecture in order to address the issues of integrating analytics into the network. The standardization of NWDAF by the 3rd Generation Partnership Project (3GPP) would enable third-party data analytics service providers to develop and provide AI-driven data analytics services to the Mobile Network Operators. The next-generation Radio Access Networks would require advanced analytics to drive closed-loop self-organizing network functions that are targeted to cognitively enhance network ef ciency and reduce the operational and capital costs of network operators. The existing solutions in this domain rely on conventional ML approaches that require the training data to be accumulated on a single data center. The concerns in this area would be the network overload and the privacy of the network operators that are sharing huge volumes of sensitive network data to the third-party Network Data Analytics Services (NDAS) executing over edge cloud infrastructures, perhaps even operated by some other players. In this paper, we propose and evaluate a Federated Learning based approach to train ML models for cognitive network management of future mobile networks that can enable network operators to get data analytics services by collaboratively building a shared learning model while retaining their critical data locally within their trusted domains.
https://doi.org/10.1109/NOMS54207.2022.9789936
Optimal input design and parameter estimation for continuous-time dynamical systems. - Ilmenau : Universitätsbibliothek, 2022. - 1 Online-Ressource (iv, 171 Seiten)
Technische Universität Ilmenau, Dissertation 2022
Diese Arbeit behandelt die Themengebiete Design of Experiments (DoE) und Parameterschätzung für zeitkontinuierliche Systeme, welche in der modernen Regelungstheorie eine wichtige Rolle spielen. Im gewählten Kontext untersucht DoE die Auswirkungen von verschiedenen Rahmenbedingungen von Simulations- bzw. Messexperimenten auf die Qualität der Parameterschätzung, wobei der Fokus auf der Anwendung der Theorie auf praxisrelevante Problemstellungen liegt. Dafür wird die weithin bekannte Fisher-Matrix eingeführt und die resultierende nicht lineare Optimierungsaufgabe angeschrieben. An einem PT1-System wird der Informationsgehalt von Signalen und dessen Auswirkungen auf die Parameterschätzung gezeigt. Danach konzentriert sich die Arbeit auf ein Teilgebiet von DoE, nämlich Optimal Input Design (OID), und wird am Beispiel eines 1D-Positioniersystems im Detail untersucht. Ein Vergleich mit häufig verwendeten Anregungssignalen zeigt, dass generierte Anregungssignale (OID) oft einen höheren Informationsgehalt aufweisen und mit genaueren Schätzwerten einhergeht. Zusätzlicher Benefit ist, dass Beschränkungen an Eingangs-, Ausgangs- und Zustandsgrößen einfach in die Optimierungsaufgabe integriert werden können. Der zweite Teil der Arbeit behandelt Methoden zur Parameterschätzung von zeitkontinuierlichen Modellen mit dem Fokus auf der Verwendung von Modulationsfunktionen (MF) bzw. Poisson-Moment Functionals (PMF) zur Vermeidung der zeitlichen Ableitungen und Least-Squares zur Lösung des resultierenden überbestimmten Gleichungssystems. Bei verrauschten Messsignalen ergibt sich daraus sofort die Problematik von nicht erwartungstreuen Schätzergebnissen (Bias). Aus diesem Grund werden Methoden zur Schätzung und Kompensation von Bias Termen diskutiert. Beitrag dieser Arbeit ist vor allem die detaillierte Aufarbeitung eines Ansatzes zur Biaskompensation bei Verwendung von PMF und Least-Squares für lineare Systeme und dessen Erweiterung auf (leicht) nicht lineare Systeme. Der vorgestellte Ansatz zur Biaskompensation (BC-OLS) wird am nicht linearen 1D-Servo in der Simulation und mit Messdaten validiert und in der Simulation mit anderen Methoden, z.B., Total-Least-Squares verglichen. Zusätzlich wird der Ansatz von PMF auf die weiter gefasste Systemklasse der Modulationsfunktionen (MF) erweitert. Des Weiteren wird ein praxisrelevantes Problem der Parameteridentifikation diskutiert, welches auftritt, wenn das Systemverhalten nicht gänzlich von der Identifikationsgleichung beschrieben wird. Am 1D-Servo wird gezeigt, dass ein Deaktivieren und Reaktivieren der PMF Filter mit geeigneter Initialisierung diese Problematik einfach löst.
https://doi.org/10.22032/dbt.52114
JUGGLER: autonomous cost optimization and performance prediction of big data applications. - In: SIGMOD '22, (2022), S. 1840-1854
Distributed in-memory processing frameworks accelerate iterative workloads by caching suitable datasets in memory rather than recomputing them in each iteration. Selecting appropriate datasets to cache as well as allocating a suitable cluster configuration for caching these datasets play a crucial role in achieving optimal performance. In practice, both are tedious, time-consuming tasks and are often neglected by end users, who are typically not aware of workload semantics, sizes of intermediate data, and cluster specification. To address these problems, we present Juggler, an end-to-end framework, which autonomously selects appropriate datasets for caching and recommends a correspondingly suitable cluster configuration to end users, with the aim of achieving optimal execution time and cost. We evaluate Juggler on various iterative, real-world, machine learning applications. Compared with our baseline, Juggler reduces execution time to 25.1% and cost to 58.1%, on average, as a result of selecting suitable datasets for caching. It recommends optimal cluster configuration in 50% of cases and near-to-optimal configuration in the remaining cases. Moreover, Juggler achieves an average performance prediction accuracy of 90%.
https://doi.org/10.1145/3514221.3517892
Joint model order estimation for multiple tensors with a coupled mode and applications to the joint decomposition of EEG, MEG Magnetometer, and Gradiometer tensors. - In: 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, (2022), S. 1186-1190
The efficient estimation of an approximate model order is essential for applications with multidimensional data if the observed low-rank data is corrupted by additive noise. Certain signal processing applications such as biomedical studies, where the data are collected simultaneously through heterogeneous sensors, share some common features, i.e., coupled factors among multiple tensors. The exploitation of this coupling can lead to a better model order estimation, especially in case of low SNRs. In this paper, we extend the rank estimation techniques, designed for a single tensor, to noise-corrupted coupled low-rank tensors that share one of their factor matrices. To this end, we consider the joint effect of the global eigenvalues (calculated from the coupled HOSVD) and exploit the exponential behavior of the resulting coupled global eigenvalues. We show that the proposed method outperforms the classical criteria and can be successfully applied to EEG, MEG Magnetometer, and Gradiometer measurements. Our real data simulation results show that the estimated rank is highly reliable in terms of dominant components extraction.
https://doi.org/10.1109/ICASSP43922.2022.9747735
Cognitive network function for mobility robustness optimization in cellular networks. - In: 2022 IEEE Wireless Communications and Networking Conference (WCNC), (2022), S. 2025-2040
Self Organizing Networks (SON) aim at automating different network management functions, thereby improving their efficiency while reducing the operational expenditures. There are several proposed SON Functions (SFs) in the standards and a crucial one among them is Mobility Robustness Optimization (MRO). It focuses on providing seamless connectivity to mobile User Equipments (UEs). While optimizing handovers, there is a trade off between the Radio Link Failures (RLFs) and ping-pongs. Research has been widely done on the applicability of machine learning algorithms in SON for making decisions in a cognitive manner. In this study, MRO problem is modeled in two ways using two different classes of machine learning algorithms - Regression (linear and non-linear) and Recommender System. The work is evaluated on a Long Term Evolution (LTE) network simulator for different traffic scenarios. It is observed that the recommender system based solution has an edge over the regression based approaches and there is an overall improvement of 3.7% in the handover performance compared to that of the baseline approach.
https://doi.org/10.1109/WCNC51071.2022.9771898
Open sub-granting radio resources in overlay D2D-based V2V communications. - In: EURASIP journal on wireless communications and networking, ISSN 1687-1499, Bd. 2022 (2022), 46, S. 1-29
Richtiger Name des Verfassers: Dariush Mohammad Soleymani
Capacity, reliability, and latency are seen as key requirements of new emerging applications, namely vehicle-to-everything (V2X) and machine-type communication in future cellular networks. D2D communication is envisaged to be the enabler to accomplish the requirements for the applications as mentioned earlier. Due to the scarcity of radio resources, a hierarchical radio resource allocation, namely the sub-granting scheme, has been considered for the overlay D2D communication. In this paper, we investigate the assignment of underutilized radio resources from D2D communication to device-to-infrastructure communication, which are moving in a dynamic environment. The sub-granting assignment problem is cast as a maximization problem of the uplink cell throughput. Firstly, we evaluate the sub-granting signaling overhead due to mobility in a centralized sub-granting resource algorithm, dedicated sub-granting radio resource (DSGRR), and then a distributed heuristics algorithm, open sub-granting radio resource (OSGRR), is proposed and compared with the DSGRR algorithm and no sub-granting case. Simulation results show improved cell throughput for the OSGRR compared with other algorithms. Besides, it is observed that the overhead incurred by the OSGRR is less than the DSGRR while the achieved cell throughput is yet close to the maximum achievable uplink cell throughput.
https://doi.org/10.1186/s13638-022-02128-0
Expanding the remote experiment set with the 3Axis Portal physical model. - In: International journal of online and biomedical engineering, ISSN 2626-8493, Bd. 18 (2022), 04, S. 21-30
The problem of insufficient variety of experiments with physical models in laboratory workshops for distance learning in the design of control systems is posed. It is caused by the limited operations with the physical model when using the interface at the level of electromechanics control. The way of solving the problem is substantiated: the transition from electromechanics control of physical models of devices to control systems for the processes of using these devices. The proposed way to increase the number of types of experiments is illustrated with examples of systems for using popular physical models of an elevator, storage warehouse and production cell. However, the main focus is on expanding the functionality of the physical model 3-Axis Portal. These possibilities are realized by equipping the portal head of the base model with new sensors and actuators, improving the loads with which the portal works and using new types of active surfaces in the working field of the portal. Based on the aggregation of the proposed nodes with the basic portal model, sixteen types of systems for setting up remote experiments are described. The structures of these systems, elements of implementation and variants of experiments are described, which relate to the design of digital control systems, visualization of sorting algorithms, technical diagnostics of electronic assemblies, pattern recognition and other relevant topics for teaching students of engineering specialties.
https://doi.org/10.3991/ijoe.v18i04.28857
Estimating food ingredient compositions based on mandatory product labeling. - In: Journal of food composition and analysis, ISSN 0889-1575, Bd. 110 (2022), 104508, S. 1-9
Having a specific understanding of the actual ingredient composition of products helps to calculate additional nutritional information, such as containing fatty and amino acids, minerals and vitamins, as well as to determine its environmental impacts. Unfortunately, producers rarely provide information on how much of each ingredient is in a product. Food manufacturers are, however, required to declare their products in terms of a label comprising an ingredient list (in descending order) and Big7 nutrient values. In this paper, we propose an automated approach for estimating ingredient contents in food products. First, we parse product labels to extract declared ingredients. Next, we exert mathematical formulations on the assumption that the weighted sum of Big7 ingredients as available from food compositional tables should resemble the product’s declared overall Big7 composition. We apply mathematical optimization techniques to find the best fitting ingredient composition estimate. We apply the proposed method to a dataset of 1804 food products spanning 11 product categories. We find that 76% of these products could be analyzed by our approach, and a composition within the prescribed nutrient tolerances could be calculated, using 20% of the allowed tolerances per Big7 ingredient on average. The remaining 24% of the food products could still be estimated when relaxing one or multiple nutrient tolerances. A study with known ingredient compositions shows that estimates are within a 0.9% difference of products’ actual recipes. Hence, the automated approach presented here allows for further analysis of large product quantities and provides possibilities for more intensive nutritional and ecological evaluations of food.
https://doi.org/10.1016/j.jfca.2022.104508