Mechanical Engineering Research Works

Permanent URI for this collectionhttp://hdl.handle.net/1903/1661

Browse

Start date: 2006Subject: search.filters.subject.machine learning

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Battery Stress Factor Ranking for Accelerated Degradation Test Planning Using Machine Learning
    (MDPI, 2021-01-30) Saxena, Saurabh; Roman, Darius; Robu, Valentin; Flynn, David; Pecht, Michael
    Lithium-ion batteries power numerous systems from consumer electronics to electric vehicles, and thus undergo qualification testing for degradation assessment prior to deployment. Qualification testing involves repeated charge–discharge operation of the batteries, which can take more than three months if subjected to 500 cycles at a C-rate of 0.5C. Accelerated degradation testing can be used to reduce extensive test time, but its application requires a careful selection of stress factors. To address this challenge, this study identifies and ranks stress factors in terms of their effects on battery degradation (capacity fade) using half-fractional design of experiments and machine learning. Two case studies are presented involving 96 lithium-ion batteries from two different manufacturers, tested under five different stress factors. Results show that neither the individual (main) effects nor the two-way interaction effects of charge C-rate and depth of discharge rank in the top three significant stress factors for the capacity fade in lithium-ion batteries, while temperature in the form of either individual or interaction effect provides the maximum acceleration.
  • Thumbnail Image
    Item
    Hand Gesture Recognition Using EGaIn-Silicone Soft Sensors
    (MDPI, 2021-05-05) Shin, Sungtae; Yoon, Han UI; Yoo, Byungseok
    Exploiting hand gestures for non-verbal communication has extraordinary potential in HCI. A data glove is an apparatus widely used to recognize hand gestures. To improve the functionality of the data glove, a highly stretchable and reliable signal-to-noise ratio sensor is indispensable. To do this, the study focused on the development of soft silicone microchannel sensors using a Eutectic Gallium-Indium (EGaIn) liquid metal alloy and a hand gesture recognition system via the proposed data glove using the soft sensor. The EGaIn-silicone sensor was uniquely designed to include two sensing channels to monitor the finger joint movements and to facilitate the EGaIn alloy injection into the meander-type microchannels. We recruited 15 participants to collect hand gesture dataset investigating 12 static hand gestures. The dataset was exploited to estimate the performance of the proposed data glove in hand gesture recognition. Additionally, six traditional classification algorithms were studied. From the results, a random forest shows the highest classification accuracy of 97.3% and a linear discriminant analysis shows the lowest accuracy of 87.4%. The non-linearity of the proposed sensor deteriorated the accuracy of LDA, however, the other classifiers adequately overcame it and performed high accuracies (>90%).
  • Thumbnail Image
    Item
    Big Machinery Data Preprocessing Methodology for Data-Driven Models in Prognostics and Health Management
    (MDPI, 2021-10-14) Cofre-Martel, Sergio; Lopez Droguett, Enrique; Modarres, Mohammad
    Sensor monitoring networks and advances in big data analytics have guided the reliability engineering landscape to a new era of big machinery data. Low-cost sensors, along with the evolution of the internet of things and industry 4.0, have resulted in rich databases that can be analyzed through prognostics and health management (PHM) frameworks. Several data-driven models (DDMs) have been proposed and applied for diagnostics and prognostics purposes in complex systems. However, many of these models are developed using simulated or experimental data sets, and there is still a knowledge gap for applications in real operating systems. Furthermore, little attention has been given to the required data preprocessing steps compared to the training processes of these DDMs. Up to date, research works do not follow a formal and consistent data preprocessing guideline for PHM applications. This paper presents a comprehensive step-by-step pipeline for the preprocessing of monitoring data from complex systems aimed for DDMs. The importance of expert knowledge is discussed in the context of data selection and label generation. Two case studies are presented for validation, with the end goal of creating clean data sets with healthy and unhealthy labels that are then used to train machinery health state classifiers.
  • Thumbnail Image
    Item
    Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals
    (MDPI, 2022-02-10) Chalamuri, Yekanth Ram; Kimball, Jacob P.; Mousavi, Azin; Zia, Jonathan S.; Rolfes, Christopher; Parreira, Jesse D.; Inan, Omer T.; Hahn, Jin-Oh
    This paper presents a novel computational algorithm to estimate blood volume decompensation state based on machine learning (ML) analysis of multi-modal wearable-compatible physiological signals. To the best of our knowledge, our algorithm may be the first of its kind which can not only discriminate normovolemia from hypovolemia but also classify hypovolemia into absolute hypovolemia and relative hypovolemia. We realized our blood volume classification algorithm by (i) extracting a multitude of features from multi-modal physiological signals including the electrocardiogram (ECG), the seismocardiogram (SCG), the ballistocardiogram (BCG), and the photoplethysmogram (PPG), (ii) constructing two ML classifiers using the features, one to classify normovolemia vs. hypovolemia and the other to classify hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) sequentially integrating the two to enable multi-class classification (normovolemia, absolute hypovolemia, and relative hypovolemia). We developed the blood volume decompensation state classification algorithm using the experimental data collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia challenges. Leave-one-subject-out analysis showed that our classification algorithm achieved an F1 score and accuracy of (i) 0.93 and 0.89 in classifying normovolemia vs. hypovolemia, (ii) 0.88 and 0.89 in classifying hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) 0.77 and 0.81 in classifying the overall blood volume decompensation state. The analysis of the features embedded in the ML classifiers indicated that many features are physiologically plausible, and that multi-modal SCG-BCG fusion may play an important role in achieving good blood volume classification efficacy. Our work may complement existing computational algorithms to estimate blood volume compensatory reserve as a potential decision-support tool to provide guidance on context-sensitive hypovolemia therapeutic strategy.
  • Thumbnail Image
    Item
    Can You Do That Again? Time Series Consolidation as a Robust Method of Tailoring Gesture Recognition to Individual Users
    (MDPI, 2022-10-03) Dankovich, Louis J. IV; Vaughn-Cooke, Monifa; Bergbreiter, Sarah
    Robust inter-session modeling of gestures is still an open learning challenge. A sleeve equipped with capacitive strap sensors was used to capture two gesture data sets from a convenience sample of eight subjects. Two pipelines were explored. In FILT a novel two-stage algorithm was introduced which uses an unsupervised learning algorithm to find samples representing gesture transitions and discards them prior to training and validating conventional models. In TSC a confusion matrix was used to automatically consolidate commonly confused class labels, resulting in a set of gestures tailored to an individual subject’s abilities. The inter-session testing accuracy using the Time Series Consolidation (TSC) method increased from a baseline inter-session average of 42.47 ± 3.83% to 93.02% ± 4.97% while retaining an average of 5.29 ± 0.46 out of the 11 possible gesture categories. These pipelines used classic machine learning algorithms which require relatively small amounts of data and computational power compared to deep learning solutions. These methods may also offer more flexibility in interface design for users suffering from handicaps limiting their manual dexterity or ability to reliably make gestures, and be possible to implement on edge devices with low computational power.
  • Thumbnail Image
    Item
    Data-Driven High-Throughput Rational Design of Double-Atom Catalysts for Oxygen Evolution and Reduction
    (Wiley, 2022-05-18) Wu, Lianping; Guo, Tian; Li, Teng
    Surging interests exist in double-atom catalysts (DACs), which not only inherit the advantages of single-atom catalysts (SACs) (e.g., ultimate atomic utilization, high activity, and selectivity) but also overcome the drawbacks of SACs (e.g., low loading and isolated active site). The design of DACs, however, remains cost-prohibitive for both experimental and computational studies, due to their huge design space. Herein, by means of density functional theory (DFT) and topological information-based machine-learning (ML) algorithms, we present a data-driven high-throughput design principle to evaluate the stability and activity of 16 767 DACs for oxygen evolution (OER) and oxygen reduction (ORR) reactions. The rational design reveals 511 types of DACs with OER activity superior to IrO2 (110), 855 types of DACs with ORR activity superior to Pt (111), and 248 bifunctional DACs with high catalytic performance for both OER and ORR. An intrinsic descriptor is revealed to correlate the catalytic activity of a DAC with the electronic structures of the DAC and its bonding carbon surface structure. This data-driven high-throughput approach not only yields remarkable prediction precision (>0.926 R-squared) but also enables a notable 144 000-fold reduction of screening time compared with pure DFT calculations, holding promise to drastically accelerate the design of high-performance DACs.