Search for: All records

Abstract Battery lifetime and reliability depend on accurate state-of-health (SOH) estimation, while complex degradation mechanisms and varying operating conditions strengthen this challenge. This study presents two physics-informed neural network (PINN) configurations, PINN-parallel and PINN-series, designed to improve SOH prediction by combining an equivalent circuit model (ECM) with a long short-term memory (LSTM) network. PINN-parallel process inputs data through parallel ECM and LSTM modules and combines their outputs for SOH estimation. On the other hand, the PINN-series uses a sequential approach that feeds ECM-derived parameters into the LSTM network to supplement temporal data analysis with physics information. Both models utilize easily accessible voltage, current, and temperature data that match realistic battery monitoring constraints. Experimental evaluations show that the PINN-series outperforms the PINN-parallel and the baseline LSTM model in accuracy and robustness. It also adapts well to different input conditions. This demonstrates that the simulated battery dynamic states from ECM increase the LSTM's ability to capture degradation patterns and improve the model's ability to explain complex battery behavior. However, a trade-off between the robustness and training efficiency of PINNs is identified. The research outcomes show the potential of PINN models (particularly the PINN-series) in advancing battery management systems, although they require considerable computational resources. 

Accurate prediction of repair durations is a challenge in product maintenance due to its implications for resource allocation, customer satisfaction, and operational performance. This study aims to develop a deep learning framework to help fleet repair shops accurately categorize repair time given product historical data. The study uses an automobile repair and maintenance dataset and creates an end-to-end predictive framework by employing a multi-head attention network designed for tabular data. The developed framework combines categorical information, transformed through embeddings and attention mechanisms, with numerical historical data to facilitate integration and learning from diverse data features. A weighted loss function is introduced to overcome class imbalance issues in large datasets. Moreover, an online learning strategy is used for continuous incremental model updates to maintain predictive accuracy in evolving operational environments. Our empirical findings demonstrate that the multi-head attention mechanism extracts meaningful interactions between vehicle identifiers and repair types compared to a feed-forward neural network. Also, combining historical maintenance data with an online learning strategy facilitates real-time adjustments to changing patterns and increases the model’s predictive performance on new data. The model is tested on real-world repair data spanning 2013 to 2020 and achieves an accuracy of 78%, with attention weight analyses illustrating feature interactions. 

Multi-lag cross-correlations (X-Corr) are essential building blocks in radar and communication for range/velocity detection and synchronization. Performing X-corrs necessitates efficient delay and correlation blocks. Traditionally, high bandwidth X-corr is performed using high-speed ADCs followed by digital multiply-and-accumulates (MACs). However, 5–20 TOPS/W X-Corr efficiencies lead to 0.1-1W per cross-correlator, limiting deployability in power-constrained applications. Alternatively, to realize X-corr using prior single-lag analog correlators, wideband analog delays (>10ns delays with 4GHz BW) should be integrated on chip to enable multiple lags. Furthermore, replicating N analog correlators, leads to an impractical chip area. Therefore, practical analog X-Corr requires: (i) high input bandwidths, (ii) long correlation length, N for high signal processing gain (SPG=10log10(N)), (iii) high compute-efficiency (>100 TOPS/W) with compute accuracy compared to digital MACs (>7-bit), (iv) single-shot readout across all N X-corr lags in a compact area. In this work, we leverage a sampling-based approach to create large analog delays and area/power-efficient four-transistor analog compute cell to present a margin-propagation (MP) based fully-analog X-Corr compute engine in 22nm SOI-CMOS achieving: (i) 1-4GS/s input, (ii) single-shot 256-length X-Corrs across all 256 lags resulting in a 256x256 X-correlator, 8.2-8.5 bit compute accuracy or hardware dynamic range (HDR) of 51-53dB, (iii) high compute efficiency of 996–1060 TOPS/W (6.6x better than SoA), (iv) high compute density of 1.3 TOPS/mm2 (7x better than SoA). We also demonstrate an X-band code-domain radar with a range resolution of 15cm across 256 range bins, supporting up to 1024 chirp averages with a 115Hz refresh rate. 

Battery lifetime and reliability depend on accurate state-of-health (SOH) estimation, while complex degradation mechanisms and varying operating conditions strengthen this challenge. This study presents two physics-informed neural network (PINN) configurations, PINN-Parallel, and PINN-Series, designed to improve SOH prediction by combining an equivalent circuit model (ECM) with a long short-term memory (LSTM) network. PINN-Parallel process input data through parallel ECM and LSTM modules and combine their outputs for SOH estimation. On the other hand, the PINN-Series uses a sequential approach that feeds ECM-derived parameters into the LSTM network to supplement temporal data analysis with physics information. Both models utilize easily accessible voltage, current, and temperature data that match realistic battery monitoring constraints. Experimental evaluations show that PINN-Series outperforms the PINN-Parallel and the baseline LSTM model in accuracy and robustness. It also adapts well to different input conditions. This demonstrates that the simulated battery dynamic states from ECM increase the LSTM's ability to capture degradation patterns and improve the model's ability to explain complex battery behavior. However, the trade-off between the robustness and training efficiency of PINNs is also discussed. The research findings show the potential of PINN models (particularly the PINN-Series) in advancing battery management systems, but the required computational resources need to be considered. 

The self-interference (SI) channels in full-duplex (FD) radios have large nano-second-scale delay spreads, which poses a significant challenge in designing SI cancelers that can emulate the SI channel over wide bandwidths. Passive implementations of high delay lines have a prohibitively large form factor and loss when implemented on silicon, whereas active implementations suffer from noise and linearity penalties. In this work, we leverage time-interleaved multi-path switched-capacitor (SC) circuits to provide large wideband delays with a small form factor and low power (LP) consumption to implement RF and baseband (BB) cancelers in an FD receiver (RX). We utilize capacitor stacking to obtain passive voltage gain to compensate for the loss of these delay elements, thus permitting an increased number of interleaved paths and, hence, a higher delay. Furthermore, to reduce the RX noise figure (NF) penalty due to injecting the cancellation signal into the receiver, we introduce a novel low-noise trans-impedance amplifier (LNTA) architecture, which injects the cancellation signal into RX and also accomplishes finite impulse response (FIR) filter weighting and summation. The FD receiver is implemented in a standard 65-nm CMOS process and operates from 0.1 to 1 GHz. The RF/BB canceler delay cells have real-/complex-valued weighting with delays ranging 

Wireless device classification techniques play a vital role in supporting spectrum awareness applications, such as spectrum access policy enforcement and unauthorized network access monitoring. Recent works proposed to exploit distortions in the transmitted signals caused by hardware impairments of the devices to provide device identification and classification using deep learning. As technology advances, the manufacturing impairment variations among devices become extremely insignificant, and hence the need for more sophisticated device classification techniques becomes inescapable. This paper proposes a scalable, RF data-driven deep learning-based device classification technique that efficiently classifies transmitting radios from a large pool of bit-similar, high-end, high-performance devices with same hardware, protocol, and/or software configurations. Unlike existing techniques, the novelty of the proposed approach lies in exploiting both the in-band and out-of-band distortion information, caused by inherent hardware impairments, to enable scalable and accurate device classification. Using convolutional neural network (CNN) model for classification, our results show that the proposed technique substantially outperforms conventional approaches in terms of both classification accuracy and learning times. In our experiments, the testing accuracy obtained under the proposed technique is about 96% whereas that obtained under the conventional approach is only about 50% when the devices exhibit very similar hardware impairments. The proposed technique can be implemented with minimum receiver design tuning, as radio technologies, such as cognitive radios, can easily allow for both in-band and out-of band sampling.