Chetan Kulkarni

The growing number of electric-powered vehicles and the associated large demand for energy storage have created the need for reliable management of a fleet of Li-ion batteries over long periods of time. The aging of such batteries is mostly attributed to capacity degradation that operators desire to monitor (and potentially, slow down) to extend battery cycle life. An important tool for this purpose are prognosis models for battery state-of-charge (SOC) and state-of-health (SOH). These models are used to forecast capacity degradation and help operators to optimize their usage profiles. In addition, they are useful tools for discharge predictions and to ensure safe and reliable operation by correctly forecasting end-of-discharge (EOD). A hybrid electro-chemistry-based model fused with neural network and Gaussian processes is presented to capture the contributions of large variations in operating conditions and temperature to SOC and SOH. The goal of this approach is to create a SOC model capable of predicting battery discharge depending on a large variety of loading conditions where, apart from the current amplitude, we also leverage data from cell temperature build-up during discharge. Additionally, our model captures the aging mechanisms in the form of degradation, which relate those to the SOH in form of battery capacity; and failure prediction through a probabilistic classifier based on Gaussian processes. For model training and validation purposes, we use an accelerated battery life testing dataset, where we applied various loading conditions to battery packs. Our model predictions for SOC, SOH and battery failure show close alignment with experimental data for all loading conditions.

With the ongoing digitization of global activities, the number of predictive maintenance datasets has been steadily growing. These datasets are often manually classified – in literature review papers – to assess their relevance for predictive maintenance applications. However, this manual approach is increasingly unsustainable, as it is time-intensive, prone to errors, and the accelerating pace at which new datasets emerge in both scientific and industrial contexts. To overcome these challenges, there is a growing need for automated solutions to curate, analyze, and categorize (tag) datasets in the literature. To this end, we propose and evaluate MAINTAG (Multi-Agent-based Predictive Maintenance Dataset Tagging System), a novel multi-agent system designed to automate the classification of predictive maintenance datasets. MAINTAG is compatible with any criteria-based taxonomy and is assessed by benchmarking its tagging accuracy against recent state-of-the-art literature. This evaluation highlights MAINTAG’s ability to replicate expert-level dataset tagging. MAINTAG resolves three critical challenges in predictive maintenance dataset tagging. The first one arises from the dramatic increase in the number of datasets. The recent growth in predictive maintenance applications has resulted in higher data volume. This makes manual tagging methods impractical and unscalable. Researchers, therefore, will struggle to manually process this flood of new data. The second challenge is related to the complexity of data classification. Each dataset consist of different data types, sources, and structures. These create additional classification difficulties. The third challenge is keeping data tagging consistent across different domains. Predictive maintenance datasets come from multiple industries, and each has its own set of standards and/or classification criteria. MAINTAG proposes a specialized multi-agent framework in response to these challenges. The framework divides the complex classification tasks into simpler and more manageable parts. The system uses specialized agents working in parallel to handle different classification tasks. These agents work together to analyze different aspects of the datasets. This system marks a major leap in autonomous data tagging. It also sets the foundation for a more scalable approach for handling surge in the predictive maintenance datasets.

Diagnostic systems are important for many aerospace systems, which are severly limited in available power, like cubesats or UAVs. Therefore, traditional diagnostics systems cannot be used due to their substantial footprint and constraints. In this paper, we present our very low power diagnostic tool SPIKE-Dx. to monitor critical systems with constrained computational and energy resources. This is made possible through spiking neural networks (SNNs), which are executable within optimized simulation environments and further implemented on on cutting-edge neuromorphic hardware. Based upon FMEA (Failure Mode and Effect Analysis) framework, Diagnostic Bayesian Networks (DBNs) can be constructed that provide powerful means for diagnostic reasoning. In this paper, we describe such DBNs and a method to automatically translate the DBN into highly structured networks of spiking neurons for execution in SPIKE-Dx.

The development of new modes of transportation such as electric vertical takeoff and landing aircraft and the use of drones for package and medical delivery have increased the demand for reliable and powerful electric batteries. Therefore, accurately predicting the degradation of a battery’s state-ofhealth (SOH) and state-of-charge (SOC) is a crucial albeit still challenging task. There is a need for models that can accurately predict the SOH and SOC while taking into account the specific characteristics of a battery cell and its usage profile. While traditional physics-based and data-driven approaches are used to monitor the SOH and SOC, they both have limitations related to computational costs or that require engineers to continually update their prediction models as new battery cells are developed and put into use in battery-powered vehicle fleets. Battery capacity degradation can vary from battery to battery and can also be influenced by changes in load due to internal thermal stress. While sophisticated electrochemistry-based models can provide precise predictions of the SOC during a discharge cycle when parameters are well-tuned, using highfidelity models for prognostics purposes can be computationally expensive. Those models also require tuning to specific battery types and at times to specific specimens, thus hindering generalization. In contrast, purely data-driven approaches can learn the relationship between input and output for SOC prediction based on load input, but they require a large and diverse training dataset and lack any physical or electrochemical understanding, making far-ahead predictions challenging if test loading conditions fall outside the training distribution. To address some of the drawbacks of the aforementioned modeling approaches, in this paper, we enhance a hybrid physics-informed machine learning version of a battery SOC model we presented in previous work to predict voltage drop during discharge. The enhanced model captures the effect of wide variation of load levels, in the form of input current, which causes large thermal stress cycles. The cell temperature build-up during a discharge cycle is used to identify temperature-sensitive model parameters. Additionally, we enhance an existing aging model built upon cumulative energy drawn by introducing the effect of the load level. We then map cumulative energy and load level to battery capacity with a Gaussian process model. To validate our approach we use a battery aging dataset collected on a self-developed testbed, where we used a wide current level range to age battery packs in accelerated fashion. Prediction results show that our model can be successfully calibrated and generalizes across all applied load levels.

A rover mission consists of visiting waypoints to gather scientific samples based on set requirements. However, rovers face operational uncertainties during the mission, affecting the performance of its electrical and mechanical components and overall mission success. Hence, it is critical to have a decision-making framework that is aware of the health state of the components when planning the path of the vehicle. In particular, battery degradation, and consequently the battery State of Health (SOH), can affect the optimality of decisions made by the autonomous system in the long term. This paper presents a decision-making system that incorporates information on the energy drawn from the battery (based on the velocity of the vehicle), terrain conditions, and model-based prognostic modules to assess impact on the battery state of charge (SoC). The decision-making system was formulated as a Markov Decision Process (MDP) to reach the goal destination by sending commands in a determined amount of time, while maintaining the battery SoC within the policy stated. The MDP problem was programmed using the open-source framework POMDPs.jl, which has a variety of online and offline solvers. To solve the MDP problem online, we used Monte Carlo Tree Search (MCTS). Results from simulations demonstrate the effect that battery degradation and charging plans have on decision-making.

The development of new modes of transportation, such as electric vertical takeoff and landing (eVTOL) aircraft and the use of drones for package and medical delivery, has increased the demand for reliable and powerful electric batteries. The most common batteries in electric-powered vehicles use Lithium-ion (Li-ion). Because of their long cycle life, they are the preferred choice for battery packs deployed over a lifespan of many years. Thus, battery aging needs to be well understood to achieve safe and reliable operation, and life cycle experiments are a crucial tool to characterize the effect of degradation and failure. With the importance of battery durability in mind, we present an accelerated Li-ion battery life cycle data set, focused on a large range of load levels, for batteries composed of two 18650 cells. We tested 26 battery packs grouped by: (i) constant or random loading conditions, (ii) loading levels, and (iii) number of load level changes. Furthermore, we conducted load cycling on second-life batteries, where surviving cells from previously-aged packs were assembled to second-life packs. The goal is to provide the PHM community with an additional data set characterized by unique features. The aggressive load profiles create large temperature increases within the cells. Temperature effects becomes therefore important for prognosis. Some samples are subject to changes in amplitude and number of load levels, thus approaching the level of variability encountered in real operations. Reassembling of survival cells into new packs created additional data that can be used to evaluate the performance of recommissioned batteries. The data set can be leveraged to develop and test models for state-of-charge and state-of-health prognosis. This paper serves as a companion to the data set. It outlines the design of experiment, shows some exemplifying time-series voltage curves and aging data, describes the testbed design and capabilities, and also provides information about the outliers detected thus far. Upon acceptance, the data set will be made available on the NASA Ames Prognostics Center of Excellence Data Repository.