Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “adaptive learning”

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.

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

At least 973 records · Page 54

Particle learning for probabilistic deterministic finite automata

The plpdfa software is a product of an LDRD project at LLNL entitked "Adaptive Sampling for Very High Throughput Data Streams" (tracking number 11-ERD-035). This software was developed by a graduate student summer intern, Chris Challis, who worked under project PI Dan Merl furing the summer of 2011. The software the source code is implementing is a statistical analysis technique for clustering and classification of text-valued data. The method had been previously published by the PI in the open literature.

Source record↗

Particle learning for probabilistic deterministic finite automata

The plpdfa software is a product of an LDRD project at LLNL entitked "Adaptive Sampling for Very High Throughput Data Streams" (tracking number 11-ERD-035). This software was developed by a graduate student summer intern, Chris Challis, who worked under project PI Dan Merl furing the summer of 2011. The software the source code is implementing is a statistical analysis technique for clustering and classification of text-valued data. The method had been previously published by the PI in the open literature.

Source record↗

Laterally Primed Adaptive Resonance Theory

LAPART is an artificial neural network algorithm written in the Python programming language. The algorithm can learn patterns using multi-dimensional hyper boxes. It can also perfrom regression and classification calculations based on learned associations.

Jones, Christian Birk↗

Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins

Machine learning (ML) methods, especially reinforcement learning (RL), have been widely considered for traffic signal optimization in intelligent transportation systems. Most of these ML methods are centralized, lacking in scalability and adaptability in large traffic networks. Further, it is challenging to train such ML models due to the lack of training platforms and/or the cost of deploying and training in a real traffic networks. This paper presents an approach for the integration of decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin (DT) to optimize traffic signals for the reduction of traffic congestion and network-wide fuel consumption related to stopping. Specifically, the DGMARL agents learn traffic state patterns and make decisions regarding traffic signal control with assistance from a Digital Twin module, which simulates and replicates the traffic behaviors of a real traffic network. The proposed approach was evaluated using PTV-Vissim [1], a microscopic traffic simulation platform. PTV-Vissim is also the simulation engine of the DT, enabling emulation and optimization of the traffic signals on the MLK Smart Corridor in Chattanooga, Tennessee. Compared to an actuated signal control baseline approach, experiment results show that Eco_PI, a developed performance measure capturing the impact of stops on fuel consumption, was reduced by 44.27% in a 24-hour and an average of 29.88% in a PM-peak-hour scenario.

Multi-Agent Reinforcement Learning, Digital Twin, ↗

Adaptive Effects on Locomotion Performance Following Exposure to a Rotating Virtual Environment

During long-duration spaceflight, astronauts experience alterations in vestibular and somatosensory cues that result in adaptive disturbances in balance and coordination upon return to Earth. These changes can pose a risk to crew safety and to mission objectives if nominal or emergency vehicle egress is required immediately following long-duration spaceflight. At present, no operational countermeasure is available to mitigate the adaptive sensorimotor component underlying the locomotor disturbances that occur after spaceflight. Therefore, the goal of this study is to develop an inflight training regimen that facilitates recovery of locomotor function after long-duration spaceflight. The countermeasure we are proposing is based on the concept of adaptive generalization. During this type of training the subject gains experience producing the appropriate adaptive motor behavior under a variety of sensory conditions and response constraints. As a result of this training a subject learns to solve a class of motor problems, rather than a specific motor solution to one problem, i.e., the subject learns response generalizability or the ability to "learn to learn." under a variety of environmental constraints. We are developing an inflight countermeasure built around treadmill exercise activities. By manipulating the sensory conditions of exercise by varying visual flow patterns, body load and speed we will systematically and repeatedly promote adaptive change in locomotor behavior. It has been shown that variable practice training increases adaptability to novel visuo-motor situations. While walking over ground in a stereoscopic virtual environment that oscillated in roll, subjects have shown compensatory torso rotation in the direction of scene rotation that resulted in positional variation away from a desired linear path. Thus, postural sway and locomotor stability in 1-g can be modulated by visual flow patterns and used during inflight treadmill training to promote adaptive generalization. The purpose of this study was to determine if adaptive modification in locomotor performance could be achieved by viewing simulated self-motion in a passive-immersive virtual ' environment over a prolonged period during treadmill locomotion.

Mulavara, A. P.↗

Automated, Unmanned Detection and Quantification of Fugitive Methane Emissions

Compressor stations used to move natural gas are one of the largest sources of fugitive methane emissions in the midstream sector, accounting for approximately 50% of all fugitive emissions (Zimmerle et al., 2015). This problem is most widespread at reciprocating compressors (Subramanian et al., 2015) where faulty seals are a key contributor to methane emissions (Johnson et al., 2015). As such, there is a significant need for a robust technology that could provide an early indication of an unexpected emission. Equally important, the technology needs to be able to account for biogenic versus anthropogenic sources of methane. One means of indirectly making this determination, is to leverage optical technologies that can autonomously pinpoint the source of such leaks. This presentation discusses recent work funded by the U.S. Department of Energy (DOE) National Energy Technology Laboratory (NETL), focused on the development of an innovative remote sensing technology that can reliably and autonomously detect fugitive methane emissions in near real-time, using computer vision and deep learning. The technology called the Smart Methane Leak Detection (SLED/M) system was initially developed to monitor facilities such as compressor stations in a stationary, pan-tilt-zoom configuration. The system has recently been adapted to monitor facilities from an unmanned aerial system (UAS). The speed and maneuverability of UAS platforms are attractive to leak detection and repair program operators, but introduce several challenges. Many existing methane detection algorithms rely on mostly static backgrounds becoming unusable with motion. In addition, top-down views of fugitive methane emissions present differently in Optical Gas Imagers (OGI) compared to looking across the plume. Our work has focused on overcoming these challenges, enhancing the operators ability to detect methane emissions, and pinpoint their sources. Another recent adaptation to SLED/M is the ability to quantify methane emissions using passive sensors (OGI, thermal camera), environmental conditions, plume modeling, and deep learning. SLED/M advances the state-of-the-art for methane emission detection and quantification by focusing on three key critical criteria for effective methane emission mitigation: (1) autonomy (no need for a human to be in the loop), (2) high reliability (low false alarm rates), and (3) real-time performance. Results from this work will be presented.

03 NATURAL GAS↗

Physics-informed Deep Reinforcement Learning-based Control in Power systems

Incorporating physics information into the deep reinforcement learning (DRL) process is a promising approach for addressing the challenges faced in learning-based control design problems for physical systems. Power grid dynamics, being a physical system, adheres to specific physical laws, constraints, as well as operational and control rules. Therefore, consideration of such physics-based law improves the learning process drastically. In general, traditional grid control schemes rely on rule-based mechanisms that cannot adapt to changing operating conditions. To improve the adaptability and computation time, recent research has seen a surge of DRL-based applications in power grid control. A generic DRL-based control design imposes the system performance requirements through the design of reward functions. In some cases, some of the important physics information is injected through this reward function. However, due to the complex dynamics and large state-action space, learning an optimal DRL policy often becomes challenging. Inspired by the latest developments in general machine learning (ML) research, power system researchers have been investigating more direct ways of incorporating physics knowledge into DRL training. This chapter specifically focuses on these aspects of physics-informed DRL designs in grid control. It discusses the significance, applications, research gaps, and open problems that need to be addressed in future research.

artificial intelligence, machine learning↗

Neural Networks for Modeling and Control of Particle Accelerators

Particle accelerators are host to myriad nonlinear and complex physical phenomena. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems, as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. The purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.

43 PARTICLE ACCELERATORS↗

POINT: Partially Observable Imitation Network for Traffic Signal Control

Smart traffic signals bring together transportation infrastructure and advance technologies to improve the mobility and efficiency of urban transportation network. Adaptive traffic signal control studies can be categorized into modeling-based approaches and learning-based approaches. In order to take advantages of these two systems, this study developed an offline-online combined Partial Observable Imitation Network for Traffic signal control (POINT). In the offline system, the traffic signal timing optimization problem was formulated as a Mixed Integer Nonlinear Programming (MINLP) given complete traffic information, i.e., second-by-second speeds and locations of all vehicles. Furthermore, the objective of MINLP is to minimize total travel delays considering individual vehicle trajectories under Connected Vehicle (CV) environment. The calculated optimal solutions under various traffic conditions were considered as the ”expert” decisions. In the online system, an imitation neural network model was developed to learn the ”expert” signal plans generated from offline system. Given partial observable traffic conditions in real time, e.g., the aggregate-level of traffic volume, the POINT model can compute the signal timing parameters in the online system. The numerical results demonstrated that the proposed method outperformed other state-of-the-art signal control method under high and unbalanced traffic demand levels in terms of reducing travel delays and queue length.

33 ADVANCED PROPULSION SYSTEMS↗

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learningautonomous systems; flight simulat↗

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learning↗

Learning-based CO 2 concentration prediction: Application to indoor air quality control using demand-controlled ventilation

There have been increasing concerns over the air quality inside buildings as high levels of bio-effluents can cause nausea, dizziness, headaches, and fatigue to the people working in those spaces. First published in 2004 as Standard 62.1, ASHRAE Standard 62.2-2019 requires highly occupied spaces to implement heating, ventilation, and air conditioning (HVAC) that can dilute contaminants produced by occupants. In this regard, occupant-centric ventilation control has been regarded as an effective practice to maintain a satisfactory indoor air quality (IAQ) when dealing with highly variable occupancy environments. However, few established models in current literature and practice consider dynamic occupancy behavior and adaptive IAQ control. To address this gap, a dynamic indoor CO2 model is constructed using machine learning algorithms to forecast CO2concentrations across a range of forecasting horizons. Herein, we tuned and compared six state-of-the-algorithms—including Support Vector Machine, Ada Boost, Random Forest, Gradient Boosting, Logistic Regression, and Multilayer Perceptron. The algorithms’ performances are validated using CO 2 and historical meteorological data collected from a campus classroom with a variable occupancy rate. Simulation results showed that Multilayer Perceptron can strongly predict the volatile CO 2 behavior and also outperforms other algorithms in terms of accuracy. Furthermore, a control strategy capable of modeling and detecting dynamic patterns of CO 2 level is utilized to modulate the ventilation rate in real-time and also reduce the energy consumption. The proposed controller reduced the HVAC fan’s energy consumption by 51.4% and provide ventilation as needed per the ASHRAE standards.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Adding dynamic rules to self-organizing fuzzy systems

This paper develops a Dynamic Self-Organizing Fuzzy System (DSOFS) capable of adding, removing, and/or adapting the fuzzy rules and the fuzzy reference sets. The DSOFS background consists of a self-organizing neural structure with neuron relocation features which will develop a map of the input-output behavior. The relocation algorithm extends the topological ordering concept. Fuzzy rules (neurons) are dynamically added or released while the neural structure learns the pattern. The DSOFS advantages are the automatic synthesis and the possibility of parallel implementation. A high adaptation speed and a reduced number of neurons is needed in order to keep errors under some limits. The computer simulation results are presented in a nonlinear systems modelling application.

Buhusi, Catalin V.↗

Using learning curves on energy-efficient technologies to estimate future energy savings and emission reduction potentials in the U.S. iron and steel industry

Increasing concerns on non-sustainable energy use and climate change spur a growing research interest in energy efficiency potentials in various critical areas such as industrial production. This paper focuses on learning curve aspects of energy efficiency measures in the U.S iron and steel sector. A number of early-stage efficient technologies (i.e., emerging or demonstration technologies) are technically feasible and have the potential to make a significant contribution to energy saving and CO 2 emissions reduction, but fall short economically to be included. However, they may also have the cost effective potential for significant cost reduction and/or performance improvement in the future under learning effects such as ‘learning-by-doing’. The investigation is carried out using ISEEM, a technology oriented, linear optimization model. We investigated how steel demand is balanced with/without the availability learning curve, compared to a Reference scenario. The retrofit (or investment in some cases) costs of energy efficient technologies decline in the scenario where learning curve is applied. The analysis also addresses market penetration of energy efficient technologies, energy saving, and CO 2 emissions in the U.S. iron and steel sector with/without learning impact. Accordingly, the study helps those who use energy models better manage the price barriers preventing unrealistic diffusion of energy-efficiency technologies, better understand the market and learning system involved, predict future achievable learning rates more accurately, and project future savings via energy-efficiency technologies with presence of learning. We conclude from our analysis that, most of the existing energy efficiency technologies that are currently used in the U.S. iron and steel sector are cost effective. Penetration levels increases through the years, even though there is no price reduction. However, demonstration technologies are not economically feasible in the U.S. iron and steel sector with the current cost structure. In contrast, some of the demonstration technologies are adapted in the mid-term and their penetration levels increase as the prices go down with learning curve. We also observe large penetration of 225kg pulverized coal injection with the presence of learning.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Aspirations and common tensions: larger lessons from the third US national climate assessment

The Third US National Climate Assessment (NCA3) was produced by experts in response to the US Global Change Research Act of 1990. Based on lessons learned from previous domestic and international assessments, the NCA3 was designed to speak to a broad public and inform the concerns of policy- and decision-makers at different scales. The NCA3 was also intended to be the first step in an ongoing assessment process that would build the nation’s capacity to respond to climate change. This concluding paper draws larger lessons from the insights gained throughout the assessment process that are of significance to future US and international assessment designers. We bring attention to process and products delivered, communication and engagement efforts, and how they contributed to the sustained assessment. Based on areas where expectations were exceeded or not fully met, we address four common tensions that all assessment designers must confront and manage: between (1) core assessment ingredients (knowledge base, institutional set-up, principled process, and the people involved), (2) national scope and subnational adaptive management information needs, (3) scope, complexity, and manageability, and (4) deliberate evaluation and ongoing learning approaches. Managing these tensions, amidst the social and political contexts in which assessments are conducted, is critical to ensure that assessments are feasible and productive, while its outcomes are perceived as credible, salient, and legitimate.

Moser, Susanne C.↗

Clustering of tethered satellite system simulation data by an adaptive neuro-fuzzy algorithm

Recent developments in neuro-fuzzy systems indicate that the concepts of adaptive pattern recognition, when used to identify appropriate control actions corresponding to clusters of patterns representing system states in dynamic nonlinear control systems, may result in innovative designs. A modular, unsupervised neural network architecture, in which fuzzy learning rules have been embedded is used for on-line identification of similar states. The architecture and control rules involved in Adaptive Fuzzy Leader Clustering (AFLC) allow this system to be incorporated in control systems for identification of system states corresponding to specific control actions. We have used this algorithm to cluster the simulation data of Tethered Satellite System (TSS) to estimate the range of delta voltages necessary to maintain the desired length rate of the tether. The AFLC algorithm is capable of on-line estimation of the appropriate control voltages from the corresponding length error and length rate error without a priori knowledge of their membership functions and familarity with the behavior of the Tethered Satellite System.

Mitra, Sunanda↗

Artificial Intelligence

Artificial intelligence is the study of intelligence agents as demonstrated by machines. It is an interdisciplinary field involving computer science as well as, various kinds of engineering and science, for example, robotics, bio-medical engineering, that accentuates automation of human acts and intelligence through machines. AI represents state-of-the-art use of machines to bring about algorithmic computation and understanding of tasks that include learning, problem solving, mapping, perception, and reasoning. Given the data and a description of its properties and relations between objects of interest, AI methods can perform the aforementioned tasks. Widely applied AI capabilities, e.g. learning, are now achievable at large scale through machine learning (ML), large volumes of data and specialized computational machines. ML encompasses learning without any kind of supervision (unsupervised learning) and learning with full supervision (supervised learning). Widely applied supervised learning techniques include deep learning and other machine learning methods that require less data than deep learning e.g. support vector machines, random forests. Unsupervised learning examples include dictionary learning, independent component analysis, and autoencoders. For application tasks with less labeled data, both supervised and unsupervised techniques can be adapted in a semi-supervised manner to produce accurate models and to increase the size of the labeled training data.

97 MATHEMATICS AND COMPUTING↗

Semi-Supervised Eigenbasis Novelty Detection

Recent discoveries in high-time-resolution radio astronomy data have focused attention on a new class of events. Fast transients are rare pulses of radio frequency energy lasting from microseconds to seconds that might be produced by a variety of exotic astrophysical phenomena. For example, X-ray bursts, neutron stars, and active galactic nuclei are all possible sources of short-duration, transient radio signals. It is difficult to anticipate where such signals might appear, and they are most commonly discovered through analysis of high-time- resolution data that had been collected for other purposes. Transients are often faint and difficult to detect, so improved detection algorithms can directly benefit the science yield of all such commensal monitoring. A new detection algorithm learns a low-dimensional linear manifold for describing the normal data. High reconstruction error indicates a novel signal that does not match the patterns of normal data. One unsupervised portion of the manifold model adapts its representation in response to recent data. A second supervised portion of the model is made of a basis trained in advance using labeled examples of RFI; this prevents false positives due to these events. For a linear model, an orthonormalization operation is used to combine these bases prior to the anomaly detection decision. Another novel aspect of the approach lies in combining basis vectors learned in an unsupervised, online fashion from the data stream with supervised basis vectors learned in advance from known examples of false alarms. Adaptive, data-driven detection is achieved that is also informed by existing domain knowledge about signals that may be statistically anomalous, but are not interesting and should therefore be ignored. The method was evaluated using data from the Parkes Multibeam Survey. This data set was originally collected to search for pulsars, which are astronomical sources that emit radio pulses at regular periods. However, several non-pulsar anomalies have recently been discovered in this dataset, making it a compelling test case. By explicitly filtering known false alarm patterns, the approach yields significantly better performance than current transient detection methods.

Wagstaff, Kiri L.↗