SEARCH · Engineering Papers

Results for “detection”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,459 records · Page 81

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

The anomalies in the high voltage converter modulator (HVCM) remain a major down time for the spallation neutron source facility, that delivers the most intense neutron beam in the world for scientific materials research. In this work, we propose neural network architectures based on Recurrent AutoEncoders (RAE) to detect anomalies ahead of time in the power signals coming from the HVCM. Bi-directional gated recurrent unit, bi-directional long-short term memory (LSTM), and convolutional LSTM (ConvLSTM) are developed, trained, and tested using real experimental signals from the HVCM module. The results show a good performance of the proposed RAE models, achieving precision up to 91%, recall up to 88%, false omission rate as low as 20% (i.e. 80% of the anomalies were detected), and area under the ROC curve up to 0.9. The three RAE models provide very comparable performance, with LSTM showing slightly better performance than GRU and ConvLSTM. The RAE models are benchmarked against other anomaly detection methods, including isolation forest, support vector machine, local outlier factor, feedforward and convolutional autoencoders, and others; showing a better performance. Here, the results of this study demonstrate the promising potential of RAE in anomaly detection for real-world power systems, and for increasing the reliability of the HVCM modules in the spallation neutron source.

42 ENGINEERING↗

DOE OSTI2020

Active Learning for Anomaly Detection in Environmental data

Due to the growing amount of data from in-situ sensors in environmental monitoring, it becomes necessary to automatically detect anomalous data points. Nowadays, this is mainly performed using supervised machine learning models, which need a fully labelled data set for their training process. However, the process of labelling data is typically cumbersome and, as a result, a hindrance to the adoption of machine learning methods for automated anomaly detection. In this work, we propose to address this challenge by means of active learning. This method consists of querying the domain expert for the labels of only a selected subset of the full data set. We show that this reduces the time and costs associated to labelling while delivering the same or similar anomaly detection performances. Finally, we also show that machine learning models providing a nonlinear classification boundary are to be recommended for anomaly detection in complex environmental data sets.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Application of a Geochemically Informed Leak Detection (GILD) Model to CO 2 Injection Sites on the United States Gulf Coast

The Gulf Coast region possesses great potential for CO 2 enhanced oil recovery (EOR) and CO 2 storage. A geochemically informed leak detection (GILD) model has been applied to CO 2 injection sites on the Gulf Coast with considerations of measurement variability. The Jasper aquifer in Montgomery County, Texas, was chosen to demonstrate the method. Based on background data from wells in the area, combinations of mineral and fluid compositions were used to create 23 scenarios for the geochemical model. The output from the geochemical model was used to identify sensitive monitoring species, and response functions were generated for these as a function of the CO 2 leakage concentration. The sources of measurement variability for background conditions were characterized from the Jasper aquifer background data, and then normalized using the coefficient of variation of each species across the monitoring wells. Bayesian belief network (BBN) models were constructed, and measurement variability of different levels were added to compare leak detection probabilities. Increasing measurement variability decreased the power to detect a leak of a given size. For a moderately high CO 2 concentration of 0.2 mol/kg, the probability of detecting this leakage effect using pH as the monitoring variable in an aquifer with calcite decreases from 98% (no measurement variability) to 61% (medium variability) to 33% (high variability). The loss in power of the sampling protocol with increasing measurement variability is similar in magnitude when Ca 2+ or HCO 3 - is used as the monitoring parameter, but only for aquifers with calcite.

58 GEOSCIENCES↗

DOE OSTI2024

EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records

Objective: Physicians and clinicians rely on data contained in electronic health records (EHRs), as recorded by health information technology (HIT), to make informed decisions about their patients. The reliability of HIT systems in this regard is critical to patient safety. Consequently, better tools are needed to monitor the performance of HIT systems for potential hazards that could compromise the collected EHRs, which in turn could affect patient safety. In this paper, we propose a new framework for detecting anomalies in EHRs using sequence of clinical events. This new framework, EHR-Bidirectional Encoder Representations from Transformers (BERT), is motivated by the gaps in the existing deep-learning related methods, including high false negatives, sub-optimal accuracy, higher computational cost, and the risk of information loss. EHR-BERT is an innovative framework rooted in the BERT architecture, meticulously tailored to navigate the hurdles in the contemporary BERT method; thus, enhancing anomaly detection in EHRs for healthcare applications.Methods: The EHR-BERT framework was designed using the Sequential Masked Token Prediction (SMTP) method. This approach treats EHRs as natural language sentences and iteratively masks input tokens during both training and prediction stages. This method facilitates the learning of EHR sequence patterns in both directions for each event and identifies anomalies based on deviations from the normal execution models trained on EHR sequences.Results: Extensive experiments on large EHR datasets across various medical domains demonstrate that EHR-BERT markedly improves upon existing models. It significantly reduces the number of false positives and enhances the detection rate, thus bolstering the reliability of anomaly detection in electronic health records. This improvement is attributed to the model’s ability to minimize information loss and maximize data utilization effectively.Conclusion: EHR-BERT showcases immense potential in decreasing medical errors related to anomalous clinical events, positioning itself as an indispensable asset for enhancing patient safety and the overall standard of healthcare services. The framework effectively overcomes the drawbacks of earlier models, making it a promising solution for healthcare professionals to ensure the reliability and quality of health data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2019

A deep learning approach to anomaly detection in geological carbon sequestration sites using pressure measurements

Carbon capture and storage (CCS) has been extensively investigated as a potential engineering measure to reduce anthropogenic carbon emission to the atmosphere. Real-time monitoring of the safety and integrity of carbon storage reservoirs is a critical aspect of any commercial-scale CCS deployment. Pressure-based sensing is cost effective, suitable for real-time monitoring, and scalable to large monitoring networks. However, questions remain on how to best harness intelligent information from the high-frequency pressure monitoring sensors to support real-time decisions. Here this work presents a deep-learning-based framework for analyzing and detecting anomalies in pressure data streams by using a convolutional long short-term memory (ConvLSTM) neural network model, which allows for the fusion of both static and dynamic reservoir data. In ConvLSTM, the convolutional neural network (CNN) is used for spatial pattern mining and the LSTM is used for temporal pattern recognition. The performance of the ConvLSTM model for real-time anomaly detection is demonstrated using a set of pressure monitoring data collected from Cranfield, Mississippi, an active enhanced-oil-recovery field. The anomaly detection model is trained using bottom-hole pressure data acquired from the base experiment (without leak event) and then tested on pressure data collected during a series of controlled CO 2 release experiments (with artificially created leak events). Results show that the ConvLSTM neural network model successfully detected anomalies in the pressure time series obtained from the controlled release experiments. Inclusion of static information into the model further improves the robustness of ConvLSTM.

13 HYDRO ENERGY↗

DOE OSTI2021

Proton-detected solid-state NMR spectroscopy of spin-1/2 nuclei with large chemical shift anisotropy

Constant-time (CT) dipolar heteronuclear multiple quantum coherence (D-HMQC) has previously been demonstrated as a method for proton detection of high-resolution wideline NMR spectra of spin-1/2 nuclei with large chemical shift anisotropy (CSA). However, 1 H transverse relaxation and t 1 -noise often reduce the sensitivity of D-HMQC experiments, preventing the theoretical gains in sensitivity provided by 1 H detection from being realized. In this paper, we demonstrate a series of improved pulse sequences for 1 H detection of spin-1/2 nuclei under fast MAS, with 195 Pt SSNMR experiments on cisplatin as an example. First, a t 1 -incrementation protocol for D-HMQC dubbed Arbitrary Indirect Dwell (AID) is demonstrated. AID allows the use of arbitrary, rotor asynchronous t 1 -increments, but removes the constant time period from CT D-HMQC, resulting in improved sensitivity by reducing transverse relaxation losses. Next, we show that short high-power adiabatic pulses (SHAPs), which efficiently invert broad MAS sideband manifolds, can be effectively incorporated into 1 H detected symmetry-based resonance echo double resonance (S-REDOR) and t 1 -noise eliminated (TONE) D-HMQC experiments. The S-REDOR experiments with SHAPs provide approximately double the dipolar dephasing, as compared to experiments with rectangular inversion pulses. We lastly show that sensitivity and resolution can be further enhanced with the use of swept excitation pulses as well as adiabatic magic angle turning (aMAT).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Hybrid data-driven and model-informed online tool wear detection in milling machines

Precision machining tool wear is responsible for low product throughput and quality. Monitoring the tool wear online is vital to prevent degradation in machining quality. However, direct real-time tool wear measurement is not practical. This paper presents residual-based anomaly detection models, combining a hybrid model comprised of a physics-based model and a data-driven model (a decision tree or a neural network) to predict signals of interest (e.g., power or forces) under nominal conditions, followed by Page’s cumulative sum test for detecting tool wear on-line using the computer numerical control machine measurements. The most informative features are ranked using dynamic programming and its approximation variants from real-time measurements and machine settings, such as the width of cut, depth of cut, feed rate and spindle speed, that serve as inputs to the predictive models. The baseline nominal model is incrementally updated with experimental data via a gradient boosted adaptation model to generate the residuals that account for discrepancies between the actual machine data under normal conditions and the baseline nominal model predictions. The hybrid model is validated against 20 Mazak milling machine experimental tests and one Haas run-to-failure experiment. The proposed anomaly detector is applied to synthetic data from simulations of the physics-based model at different operating conditions, measurement noise levels, and tool wear levels, and the methods were able to achieve an overall 92% accuracy in data with 1% noise. The anomaly detection methods based on hybrid model reduced the false alarms of either the data-driven or physical-based models alone, and are found to be capable of good online detection of tool wear.

42 ENGINEERING↗

DOE OSTI2023

Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes

The ability of recurrent neural networks (RNN) to model nonlinear dynamics of high dimensional process data has enabled data-driven RNN-based fault detection algorithms. Previous studies have focused on detecting faults by identifying the discrepancies in data distribution between the faulty and normal data, as reflected in prediction errors generated by RNN models. However, in industrial processes, variations in data distribution can also result from changes in normal control setpoints and compensatory control adjustments in response to disturbances, making it hard to differentiate between normal and faulty conditions. This paper proposes a fault detection method utilizing a long short-term memory (LSTM) encoder–decoder structure with regularized hidden dynamics and reversible instance normalization (RevIN) to compactly represent high-dimensional measurements for effective monitoring. During training, the hidden states of the model are regularized to form a low-dimensional latent space representation of the original multivariate time series data. As a result, the prediction errors of the latent states can be used to monitor the abnormal dynamic variations, while the reconstruction errors of the measured variables are used to monitor the abnormal static variations. Furthermore, the proposed indices can reflect operating conditions, even when the distribution of test data changes, which helps distinguish faults from normal adjustments and disturbances that controllers can settle. Here, data from numerical simulation and the Tennessee Eastman process are used to illustrate the effectiveness of the proposed fault detection method.

42 ENGINEERING↗

DOE OSTI2016

Mesoporous aluminium organophosphonates: a reusable chemsensor for the detection of explosives

Rapid and sensitive detection of explosives is in high demand for homeland security and public safety. In this work, electron-rich of anthracene functionalized mesoporous aluminium organophosphonates (En-AlPs) were synthesized by a one-pot condensation process. The mesoporous structure and strong blue emission of En-AlPs were confirmed by the N{sub 2} adsorption-desorption isotherms, transmission electron microscopy images and fluorescence spectra. The materials En-AlPs can serve as sensitive chemosensors for various electron deficient nitroderivatives, with the quenching constant and the detection limit up to 1.5×10{sup 6} M{sup −1} and 0.3 ppm in water solution. More importantly, the materials can be recycled for many times by simply washed with ethanol, showing potential applications in explosives detection. - Graphical abstract: Electron-rich of anthracene functionalized mesoporous aluminium organophosphonates can serve as sensitive and recycled chemosensors for nitroderivatives with the quenching constant up to 1.5×10{sup 6} M{sup −1} in water solution. Display Omitted - Highlights: • Anthracene functionalized mesoporous aluminium organophosphonates were synthesized. • The materials serve as sensitive chemosensors for nitroderivatives. • The materials can be recycled for many times by simply washed with ethanol. • The materials show potential applications in explosives detection.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2018

Preparation and application of Mn-Doped Zn0.5Cd0.5S @ ZnS nanorods with high quantum yield as sensitive fluorescence probe for detection of glucose

Highlights: • Mn:ZCS@ZnS NRs are successfully synthesized by a facile thermal decomposition approach. • Mn:ZCS@ZnS NRs exhibit high photoluminescence with quantum yield reaching up to 85%. • Mn:ZCS@ZnS NRs with high quantum yield can be used as sensitive probe for glucose detection. - Abstract: Blood glucose level is a crucial clinical index of monitoring diabetes patients. Glucose sensors based on fluorescent quantum dots have received extensive attention. Herein, a highly photoluminescent Mn-doped Zn{sub 0.5}Cd{sub 0.5}S capped ZnS nanorods (Mn:ZCS@ZnS NRs) are successfully synthesized by a facile thermal decomposition approach. The maximum fluorescence quantum yield (QY) of as-prepared Mn:ZCS@ZnS NRs enable to reach 85% by optimizing Mn-doping level, temperature, time and ZnS coating. The results of probe experiments for glucose indicate that H{sub 2}O{sub 2} generated from the oxidation of glucose in presence of glucose oxidase (GOD) can lead to a pronounced decrease of fluorescence intensity of Mn:ZCS@ZnS NRs samples. Two distinct linear detections within the range from 50 μM to 300 μM and from 200 μM to 1000 μM are obtained and the limit of detection can reach to 100 nM. Preliminary study exhibits that Mn:ZCS@ZnS nanorods with high fluorescence quantum yield can be used as an efficient fluorescent probe for glucose detection.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2019

Development of a rapid viability polymerase chain reaction method for detection of Yersinia pestis

Due to the occurrence of natural plague outbreaks and its historical usage as a biological weapon, Yersinia pestis is considered one of the high-priority biological threat agents. It can remain viable in certain environments including water for >100 days. Because of its slow-growth characteristic, it usually takes three or more days to detect and confirm the identity of viable Y. pestis cells by PCR, serological, or biochemical assays when using the traditional microbiological plate-culture-based analysis, and that too, assuming faster growing microbes present in a water sample do not mask the Y. pestis colonies and interfere with analysis. Therefore, a rapid-viability Polymerase Chain Reaction (RV-PCR) method was developed for detection of Y. pestis . The RV-PCR method combines 24 h-incubation broth culture in a 48-well plate, and pre- and post-incubation differential PCR analyses, thereby allowing for rapid and high-throughput sample analysis compared with the current plate culture method. One chromosomal and two plasmid gene target-based real-time PCR assays were down-selected, showing ca. 10 genome equivalent detection; the chromosomal assay was then used for RV-PCR method development. A 10 1 -cell level (10–99 cells) sensitivity of detection was demonstrated even with complex sample backgrounds including known PCR inhibitors (ferrous sulfate and humic acid), as well as metal oxides and microbes present in Arizona Test Dust (ATD). The method sensitivity was maintained in the presence of dead Y. pestis cells up to 10 4 cells per sample. While affording high-throughput and rapid sample analysis, the 48-well plate format used in this method for sample enrichment significantly reduced labor requirements and generation of BioSafety Level-3 (BSL-3) laboratory waste as compared to the usual microbiological plate-culture-based methods. In conclusion, this method may serve as a model for other vegetative bacterial pathogens.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2019

Rapid viability polymerase chain reaction method for detection of Francisella tularensis

Francisella tularensis, which causes potentially fatal tularemia, has been considered an attractive agent of bioterrorism and biological warfare due to its low infectious dose, reported environmental persistence, and ability to be transmitted to humans via multiple exposure routes. Additionally, due to slow growth on even selective culture media, detection of viable F. tularensis from environmental and drinking water samples, usually takes >3 days. Therefore, a rapid viability polymerase chain reaction (RV-PCR) method was developed to detect and identify viable F. tularensis cells in environmental samples. The method uses a change in PCR response during high throughput (48-well) sample incubation in Brain Heart Infusion/Vitox/Fildes/Histidine growth medium to detect viable F. tularensis presence, which is at least two times faster than the current plate culture-based method. Using the method, 101 to 102 live F. tularensis cells were detected in simulated complex sample matrices containing chemical and biological interferences.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

RAMM-TM for detection of gas leakage from canisters containing spent nuclear fuel

Remote Area Modular Monitoring (RAMM) for canister surface temperature measurement (TM), or RAMM-TM, is a novel remote monitoring device for detection of gas leakage based on surface temperature measurements of canisters containing spent nuclear fuel. Here we describe the development of RAMM-TM, as is the demonstration of its performance in detecting canister gas leakage from a small, simulated chloride-induced stress corrosion crack in experiments using a 1/4.5-scale model cask. Both helium and air gas leakage from a canister were detected within hours after the start of the leakage. The change in surface temperatures at the top and bottom of the canister (ΔTBT) during gas leakage (depressurization) triggered automatic alarms, providing a sound basis for early detection of gas leakage from the canister. This methodology would allow consequence management through the implementation of mitigatory actions to continue effective aging management and to reduce risks to public safety, health, and the environment.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2016

Detection and attribution of climate extremes in the observed record

We present an overview of practices and challenges related to the detection and attribution of observed changes in climate extremes. Detection is the identification of a statistically significant change in the extreme values of a climate variable over some period of time. Issues in detection discussed include data quality, coverage, and completeness. Attribution takes that detection of a change and uses climate model simulations to evaluate whether a cause can be assigned to that change. Additionally, we discuss a newer field of attribution, event attribution, where individual extreme events are analyzed for the express purpose of assigning some measure of whether that event was directly influenced by anthropogenic forcing of the climate system.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Metal–Organic Framework-Based Microfluidic Impedance Sensor Platform for Ultrasensitive Detection of Perfluorooctanesulfonate

The growing global concerns to public health from human exposure to perfluorooctanesulfonate (PFOS) requires rapid, sensitive, in-situ detection where current, state-of-the-art techniques are yet to adequately meet sensitivity and selectivity standards of the real-world. This work presents, for the first time, a synergistic approach for the targeted affinity-based capture of PFOS using a porous sorbent probe that enhances detection sensitivity by embedding it on a microfluidic conductive platform. This novel sorbent-containing platform functions as an electrochemical sensor to directly measure PFOS concentration through a proportional change in electrical response (increase in impedance). The extremely high surface area and pore volume of mesoporous metal-organic framework (MOF) Cr-MIL-101 is used as the probe for targeted PFOS capture based on the affinity of the chromium center towards both the fluorine tail groups as well as the sulfonate functionalities as demonstrated by spectroscopic (NMR and XPS) and microscopic (TEM) studies. Answering the need for an ultrasensitive PFOS detection technique, we are embedding these MOF capture probes inside a microfluidic channel, sandwiched between interdigitated microelectrodes (IDµE). The nanoporous geometry increases the signal to noise ratio of interdigitated microelectrodes tremendously increasing sensitivity; this in combination with the ability of the capture probes to interact with the PFOS at the molecular level and effectively transduce that response electrochemically has allowed us achieve a PFOS detection limit of 0.5 ng/L, which is unprecedented for in-situ analytical PFOS sensors and even comparable to quantification limits achieved using state-of-the-art ex situ techniques.

36 MATERIALS SCIENCE↗

DOE OSTI2016

Improved explosive collection and detection with rationally assembled surface sampling materials

Sampling and detection of trace explosives is a key analytical process in modern transportation safety. In this work we have explored some of the fundamental analytical processes for collection and detection of trace level explosive on surfaces with the most widely utilized system, thermal desorption IMS. The performance of the standard muslin swipe material was compared with chemically modified fiberglass cloth. The fiberglass surface was modified to include phenyl functional groups. When compared to standard muslin, the phenyl functionalized fiberglass sampling material showed better analyte release from the sampling material as well as improved response and repeatability from multiple uses of the same swipe. The improved sample release of the functionalized fiberglass swipes resulted in a significant increase in sensitivity. Various physical and chemical properties were systematically explored to determine optimal performance. The results herein have relevance to improving the detection of other explosive compounds and potentially to a wide range of other chemical sampling and field detection challenges.

Explosive detection↗

DOE OSTI2013

Standoff alpha radiation detection via excited state absorption of air

A standoff alpha radiation detection technique based on the physical mechanism of excited state absorption of air molecules was explored and is presented in this paper. Instead of directly detecting the radiation via measuring the intensity of radiation induced air fluorescence, the radiation is detected via the excited state absorption of alpha radiation excited/ionized air molecules. Both theoretical analyses and experimental verifications were conducted. The experimental results confirmed that the radiation could be detected via excited state absorption of radiation excited/ionized air molecules at a 10 m standoff distance, which was consistent with the theoretical analyses.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2013

Low background high efficiency radiocesium detection system based on positron emission tomography technology

After the 2011 nuclear power plant accident at Fukushima, radiocesium contamination in food became a serious concern in Japan. However, low background and high efficiency radiocesium detectors are expensive and huge, including semiconductor germanium detectors. To solve this problem, we developed a radiocesium detector by employing positron emission tomography (PET) technology. Because {sup 134}Cs emits two gamma photons (795 and 605 keV) within 5 ps, they can selectively be measured with coincidence. Such major environmental gamma photons as {sup 40}K (1.46 MeV) are single photon emitters and a coincidence measurement reduces the detection limit of radiocesium detectors. We arranged eight sets of Bi{sub 4}Ge{sub 3}O{sub 12} (BGO) scintillation detectors in double rings (four for each ring) and measured the coincidence between these detectors using PET data acquisition system. A 50 × 50 × 30 mm BGO was optically coupled to a 2 in. square photomultiplier tube (PMT). By measuring the coincidence, we eliminated most single gamma photons from the energy distribution and only detected those from {sup 134}Cs at an average efficiency of 12%. The minimum detectable concentration of the system for the 100 s acquisition time is less than half of the food monitor requirements in Japan (25 Bq/kg). These results show that the developed radiocesium detector based on PET technology is promising to detect low level radiocesium.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗