Standard groupware products do not fulfill the specific requirements of various application areas, due to technical restrictions, lack of flexibility or non-availability of adapted interfaces. In view of this situatio...
详细信息
Model-based state estimation of lithium-ion batteries relies on a robust, yet efficient parametrization of the underlying model under different conditions, which can be analyzed and improved through the lenses of Desi...
详细信息
Model-based state estimation of lithium-ion batteries relies on a robust, yet efficient parametrization of the underlying model under different conditions, which can be analyzed and improved through the lenses of Design-of-Experiments (DoE) methodologies. This paper presents parametrized physics-informed deep operator networks (PI-DeepONets) trained without any measured or synthetic data to predict solutions of a Single-Particle-Model for varying current profiles and electrode-specific diffusivity values. The prediction accuracy is evaluated based on three use cases representing three sets of current profiles featuring constant, smoothly time-dependent and non-smooth pulse profiles. After training PI-DeepONets, lithium concentration profiles are predicted within milliseconds achieving normalized percentage errors on the particle surfaces below 0.3% for constant or smoothly time-dependent current profiles and below 2% for non-smooth pulse profiles. The fast approximation of Fisher-Information-Matrices (FIMs) based on the trained PI-DeepONets offers additional speed-up potentials for DoE methodologies and yields a speed-up factor of 30 in the considered use case when compared to classical FIM approximation via finite differences on numerical reference solutions.
In medical biotechnology there is a growing need for efficient and reliable single cell analysis techniques. Fluorescence microscopy in combination with image analysis solution is a powerful tool for the characterizat...
详细信息
We propose the usage of a novel 3D-Sensor for Visual Servoing in order to avoid the problem of depth estimation that is to be solved in most servoing schemes. The sensor used in this paper is based on the time-of-flig...
详细信息
ISBN:
(纸本)9783902661654
We propose the usage of a novel 3D-Sensor for Visual Servoing in order to avoid the problem of depth estimation that is to be solved in most servoing schemes. The sensor used in this paper is based on the time-of-flight principle and returns a depth image along with an intensity image. As these are acquired by the same CCD array, no calibration between them is necessary. As an application example a position-based eye-in hand servoing scheme is presented with the sensor mounted on the end-effector of a pan-tilt unit. An experimental tracking task was defined as follows: a sphere moving with respect to the pan-tilt unit has to be kept in the optical centre of the camera. We implemented velocity-based control of the manipulator joints and obtained the following results: the pan-tilt unit was operated at a control frequeny of 17.5 Hz and - starting from a skewed pan and tilt - the sphere could be regulated to the optical center in less than one second.
Uncertainties complicate the task of designing optimal controllers for complex systems. This work introduces FMUGym, a novel open source interface that connects reinforcement learning libraries following the Gymnasium...
详细信息
Even experts struggle with the decision which processes should be automated and which not. The best solution these days is the so-called Automation Potential Analyses (APA). However, the APA can just be applied to alr...
详细信息
Automated screening of the selectivity, toxicity, metabolism and absorption of drugs could support the development of novel innovative diagnosis and therapeutics. The biotechnological research demands on effective met...
详细信息
The digital twin in manufacturing, also called digital factory twin (DFT), is not only a recent technology but also a polymorphic concept which generates a profusion of state-of-the-art work from industry and research...
详细信息
Wireless networks are indispensable in today’s production and automation. In an industrial environment, they are used in particular for networking moving or inaccessible parts of a factory. Due to difficult signal pr...
详细信息
A method of optimizing the control parameter of wearable exoskeletons for industrial applications using subjective feedbacks is introduced in this paper. The human sensory system is explained and a method of mapping t...
详细信息
暂无评论