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. 

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. 

Informed decision-making for sustainable manufacturing requires accurate manufacturing process environmental impact models with uncertainty quantification (UQ). For emerging manufacturing technologies, there is often insufficient process data available to derive accurate data-driven models. This paper explores an alternative mechanistic modeling approach using easy-to-access data from a given machine to perform Bayesian inference and reduce the uncertainty of model parameters. First, we derive mechanistic models of the cumulative energy demand (CED) for making aluminum (AlSi10) and nylon (PA12) parts using laser powder bed fusion (L-PBF). Initial parametric uncertainty is assigned to the model inputs informed by literature reviews and interviews with industry experts. Second, we identify the most critical sources of uncertainty using variance-based global sensitivity analyses; therefore, reducing the dimension of the problem. For metal and polymer L-PBF, critical uncertainty is related to the adiabatic efficiency of the process (a measure of the efficiency with which the laser energy is used to fuse the powder) and the recoating time per layer between laser scans. Data pertinent to both of these parameters include the part geometry (height and volume) and total build time. Between three and eight data points on part geometry and build time were collected on two different L-PBF machines and Bayesian inference was performed to reduce the uncertainty of the adiabatic efficiency and recoating time per layer on each machine. This approach was validated by subsequently taking direct parameter measurements on these machines during operation. The delivered electricity uncertainty is reduced by 40-70% after performing inference, highlighting the potential to construct accurate energy and environmental impact models of manufacturing processes using small easy-to-access datasets without interfering with the operations of the manufacturing facility. 

Abstract A workshop on Challenges in Representing Manufacturing Processes for Systematic Sustainability Assessments, jointly sponsored by the U.S. National Science Foundation, the U.S. National Institute of Standards and Technology, ASTM International, the American Society of Mechanical Engineers, and the Society of Manufacturing Engineers, was held in College Station, Texas on June 21, 2018. The goals of the workshop were to identify research needs supporting manufacturing process characterization, define limitations in associated education practices, and emphasize on challenges to be pursued by the advanced manufacturing research community. An important aspect surrounded the introduction and development of reusable abstractions of manufacturing processes (RAMP), which are standard representations of unit manufacturing processes to support the development of metrics, methods, and tools for the analysis of manufacturing processes and systems. This paper reports on the workshop activities and findings, which span the improvement of engineering education, the understanding of process physics and the influence of novel materials and manufacturing processes on energy and environmental impacts, and approaches for optimization and decision-making in the design of manufacturing systems. A nominal group technique was used to identify metrics, methods, and tools critical to advanced manufacturing industry as well as highlight the associated research challenges and barriers. Workshop outcomes provide a number of research directions that can be pursued to address the identified challenges and barriers.