Department of Engineering Sciences, University of Agder, NorwayAbstract: Compressed sensing enables sparse sampling but relies on generic bases and random measurements, limiting efficiency and reconstruction quality. Optimal sensor placement uses historcal data to design tailored sampling patterns, yet its fixed, linear bases cannot adapt to nonlinear or sample-specific variations. Generative model-based compressed sensing improves reconstruction using deep generative priors but still employs suboptimal random sampling. We propose an adaptive sparse sensing framework that couples a variational autoencoder prior with reinforcement learning to select measurements sequentially. Experiments show that this approach outperforms CS, OSP, and Generative model-based reconstruction from sparse measurements.

This paper presents an innovative Transformer-based deep learning strategy for optimizing the placement of sensors aiming at structural health monitoring of semiconductor probe cards. Failures in probe cards, including substrate cracks and loosened screws, would critically affect semiconductor manufacturing yield and reliability. Some failure modes could be detected by equipping a probe card with adequate sensors. Frequency response functions from simulated failure scenarios are adopted within a finite element model of a probe card. A comprehensive dataset, enriched by physics-informed scenario expansion and physics-aware statistical data augmentation, is exploited to train a hybrid Convolutional Neural Network and Transformer model. The model achieves high accuracy (99.83%) in classifying the probe card health states (baseline, loose screw, crack) and an excellent crack detection recall (99.73%). Model robustness is confirmed through a rigorous framework of 3 repetitions of 10-fold stratified cross-validation. The attention mechanism also pinpoints critical sensor locations: an analysis of the attention weights offers actionable insights for designing efficient, cost-effective monitoring systems by optimizing sensor configurations. This research highlights the capability of attention-based deep learning to advance proactive maintenance, enhancing operational reliability and yield in semiconductor manufacturing.

This paper introduces a sensor steering methodology based on deep reinforcement learning to enhance the predictive accuracy and decision support capabilities of digital twins by optimising the data acquisition process. Traditional sensor placement techniques are often constrained by one-off optimisation strategies, which limit their applicability for online applications requiring continuous informative data assimilation. The proposed approach addresses this limitation by offering an adaptive framework for sensor placement within the digital twin paradigm. The sensor placement problem is formulated as a Markov decision process, enabling the training and deployment of an agent capable of dynamically repositioning sensors in response to the evolving conditions of the physical structure as represented by the digital twin. This ensures that the digital twin maintains a highly representative and reliable connection to its physical counterpart. The proposed framework is validated through a series of comprehensive case studies involving a cantilever plate structure subjected to diverse conditions, including healthy and damaged conditions. The results demonstrate the capability of the deep reinforcement learning agent to adaptively reposition sensors improving the quality of data acquisition and hence enhancing the overall accuracy of digital twins.

Our work aims at simulating and predicting the temperature conditions inside a power transformer using Physics-Informed Neural Networks (PINNs). The predictions obtained are then used to determine the optimal placement for temperature sensors inside the transformer under the constraint of a limited number of sensors, enabling efficient performance monitoring. The method consists of combining PINNs with Mixed Integer Optimization Programming to obtain the optimal temperature reconstruction inside the transformer. First, we extend our PINN model for the thermal modeling of power transformers to solve the heat diffusion equation from 1D to 2D space. Finally, we construct an optimal sensor placement model inside the transformer that can be applied to problems in 1D and 2D.

In the current data-intensive era, big data has become a significant asset for Artificial Intelligence (AI), serving as a foundation for developing data-driven models and providing insight into various unknown fields. This study navigates through the challenges of data uncertainties, storage limitations, and predictive data-driven modeling using big data. We utilize Robust Principal Component Analysis (RPCA) for effective noise reduction and outlier elimination, and Optimal Sensor Placement (OSP) for efficient data compression and storage. The proposed OSP technique enables data compression without substantial information loss while simultaneously reducing storage needs. While RPCA offers an enhanced alternative to traditional Principal Component Analysis (PCA) for high-dimensional data management, the scope of this work extends its utilization, focusing on robust, data-driven modeling applicable to huge data sets in real-time. For that purpose, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network, are applied to model and predict data based on a low-dimensional subset obtained from OSP, leading to a crucial acceleration of the training phase. LSTMs are feasible for capturing long-term dependencies in time series data, making them particularly suited for predicting the future states of physical systems on historical data. All the presented algorithms are not only theorized but also simulated and validated using real thermal imaging data mapping a ship's engine.

However, determining the most effective sensor placement for optimal classification performance remains challenging. This paper introduces a novel methodology to resolve this issue, using real-time 2D pose estimations derived from video recordings of target activities. The derived skeleton data provides a unique strategy for identifying the optimal sensor location. We validate our approach through a feasibility study, applying inertial sensors to monitor 13 different activities across ten subjects. Our findings indicate that the vision-based method for sensor placement offers comparable results to the conventional deep learning approach, demonstrating its efficacy.

Tall buildings exposed to wind experience wind-induced loads that create pressure on the building envelope, and their integral effects cause the structure to move in the dominant directions, namely along-wind, across-wind, and torsional [1, 2, 3]. The description of the pressure field around a building does not lend itself to a simple functional relationship with approach flow turbulence. As a result, calls for reliance on wind tunnel experiments have been made. These tests rely heavily on pressure taps connected to pressure sensors to monitor pressure fields over the building surface. A basic question is where to deploy available sensors to accurately predict and reconstruct the structure of a wind pressure field from limited and noisy sensor outputs. In fact, the optimal sensor placement problem has garnered considerable attention for a long time, as fast data acquisition, analysis, and decision in high-performance control for complex systems can be archived with a small number of measurements at limited locations. In practice, the best locations for sensors in regular structures with simple geometry and a small number of degrees of freedom can be determined empirically using engineering judgment and past experience. However, for a complicated large-scale structure, a systematic and efficient approach is required because the solution space is far beyond the capabilities of hand calculation [4, 5, 6, 7, 8]. Mathematically, the goal is to find m positions from a set of n positions that maximize the information about the behaviors of a structural system: n! c =

This paper explores a new sequential selection framework for the optimal sensor placement (OSP) in Electrocardiography imaging networks (ECGI). The proposed methodology incorporates the use a recent experimental design method for the sequential selection of landmarkings on biological objects, namely, Gaussian process landmarking (GPLMK) for better exploration of the candidate sensors. The two experimental design methods work as a source of the training and the validation locations which is fitted using a spatiotemporal Gaussian process (STGP). The STGP is fitted using the training set to predict for the current validation set generated using GPLMK, and the sensor with the largest prediction absolute error is selected from the current validation set and added to the selected sensors. Next, a new validation set is generated and predicted using the current training set. The process continues until selecting a specific number of sensor locations. The study is conducted on a dataset of body surface potential mapping (BSPM) of 352 electrodes of four human subjects. A number of 30 sensor locations is selected using the proposed algorithm. The selected sensor locations achieved average $R^2 = 94.40 \%$ for estimating the whole-body QRS segment. The proposed method adds to design efforts for a more clinically practical ECGI system by improving its wearability and reduce the design cost as well.