Self-organizing and learning control systems.
Self organizing and learning control systems, adaptive systems theory and defining self organizing control systems
Barron, R. L.↗
SEARCH · Search NASA
Results for “learning systems”
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.
Learning dynamical systems from data: An introduction to physics-guided deep learning
Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expensive numerical integration, requiring significant computational resources and domain expertise. While deep learning (DL) provides efficient alternatives for modeling complex dynamics, they require a large amount of labeled training data. Furthermore, its predictions may disobey the governing physical laws and are difficult to interpret. Physics-guided DL aims to integrate first-principled physical knowledge into data-driven methods. It has the best of both worlds and is well equipped to better solve scientific problems. Recently, this field has gained great progress and has drawn considerable interest across discipline Here, we introduce the framework of physics-guided DL with a special emphasis on learning dynamical systems. We describe the learning pipeline and categorize state-of-the-art methods under this framework. We also offer our perspectives on the open challenges and emerging opportunities.
97 MATHEMATICS AND COMPUTING↗
Learning Management System User Requirements for the National Nuclear Security Administration's International Nuclear Safeguards Engagement Program
The National Nuclear Security Administration's (NNSA) International Nuclear Safeguards Engagement Program (INSEP) is considering investing in new tools that would allow the program to support its partner states from a distance. At the same time, the program is considering approaches that would allow several organizations, including NNSA, IAEA, national laboratories and contractor staff, to collaborate in the development and maintenance of instructional content. Software systems known as Learning Management Systems (LMSs) might represent a mechanism through which INSEP could accomplish these goals (collaborative development and remote support). To assess the usefulness of an LMS, INSEP has specified its needs for delivering online training and compared those needs to the capability of a range of LMSs. This comparison will allow INSEP to determine whether an LMS would be a useful tool and may set the stage for a "make-buy" decision in the future. The study team concluded that INSEP's content development and delivery needs align well with the capabilities of the leading LMSs on the market today and that that INSEP performance requirements allow for a customized approach using existing training portals that are already available to NNSA. Additional work would be required to specify the desired processes for developing online training and outreach materials, structuring the databases, specifying the data that should be collected, and detailing the desired system reports and documentation.
96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
Assuring Safety-Critical Machine Learning Enabled Systems: Challenges and Promise
Machine learning is increasingly being used in safety-critical systems, where the public safety requires a rigorous assurance process. We shall outline how assurance processes work for conventional systems and identify the primary difficulty in applying them to machine learning enabled systems. We will then outline a path forward including identifying where considerable basic research remains
Safety-critical systems↗
Assuring Safety-Critical Machine Learning Enabled Systems: Challenges and Promise
Machine learning is increasingly being used in safety-critical systems, where the public safety requires a rigorous assurance process. We shall outline how assurance processes work for conventional systems and identify the primary difficulty in applying them to machine learning enabled systems. We will then outline a path forward including identifying where considerable basic research remains.
machine learning↗
An overview of the EOSDIS V0 information management system: Lessons learned from the implementation of a distributed data system
The EOSDIS Version 0 system, released in July, 1994, is a working prototype of a distributed data system. One of the purposes of the V0 project is to take several existing data systems and coordinate them into one system while maintaining the independent nature of the original systems. The project is a learning experience and the lessons are being passed on to the architects of the system which will distribute the data received from the planned EOS satellites. In the V0 system, the data resides on heterogeneous systems across the globe but users are presented with a single, integrated interface. This interface allows users to query the participating data centers based on a wide set of criteria. Because this system is a prototype, we used many novel approaches in trying to connect a diverse group of users with the huge amount of available data. Some of these methods worked and others did not. Now that V0 has been released to the public, we can look back at the design and implementation of the system and also consider some possible future directions for the next generation of EOSDIS.
Ryan, Patrick M.↗
Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems
The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a lookup table for the world model and implement the Q function with a neural net. Time limitations prevented the combination of these two approaches. The final section discusses the results and gives clues for future work.
Lima, Pedro↗
Learning control system design based on 2-D theory - An application to parallel link manipulator
An approach to iterative learning control system design based on two-dimensional system theory is presented. A two-dimensional model for the iterative learning control system which reveals the connections between learning control systems and two-dimensional system theory is established. A learning control algorithm is proposed, and the convergence of learning using this algorithm is guaranteed by two-dimensional stability. The learning algorithm is applied successfully to the trajectory tracking control problem for a parallel link robot manipulator. The excellent performance of this learning algorithm is demonstrated by the computer simulation results.
Geng, Z.↗
Engineering Lessons Learned and Systems Engineering Applications
Systems Engineering is fundamental to good engineering, which in turn depends on the integration and application of engineering lessons learned. Thus, good Systems Engineering also depends on systems engineering lessons learned from within the aerospace industry being documented and applied. About ten percent of the engineering lessons learned documented in the NASA Lessons Learned Information System are directly related to Systems Engineering. A key issue associated with lessons learned datasets is the communication and incorporation of this information into engineering processes. As part of the NASA Technical Standards Program activities, engineering lessons learned datasets have been identified from a number of sources. These are being searched and screened for those having a relation to Technical Standards. This paper will address some of these Systems Engineering Lessons Learned and how they are being related to Technical Standards within the NASA Technical Standards Program, including linking to the Agency's Interactive Engineering Discipline Training Courses and the life cycle for a flight vehicle development program.
Gill, Paul S.↗
Consumer Guide to Small Wind Energy Systems
Learn how to use a small wind energy system to produce electricity to power your home. This fact sheet from Energy Saver includes information on how small wind energy systems can work for homes and how to determine whether your site is a good candidate for a small wind turbine.
small wind energy system, wind turbine, Energy Sav↗
Customizing the JPL Multimission Ground Data System: Lessons learned
The Multimission Ground Data System (MGDS) at NASA's Jet Propulsion Laboratory has brought improvements and new technologies to mission operations. It was designed as a generic data system to meet the needs of multiple missions and avoid re-inventing capabilities for each new mission and thus reduce costs. It is based on adaptable tools that can be customized to support different missions and operations scenarios. The MGDS is based on a distributed client/server architecture, with powerful Unix workstations, incorporating standards and open system architectures. The distributed architecture allows remote operations and user science data exchange, while also providing capabilities for centralized ground system monitor and control. The MGDS has proved its capabilities in supporting multiple large-class missions simultaneously, including the Voyager, Galileo, Magellan, Ulysses, and Mars Observer missions. The Operations Engineering Lab (OEL) at JPL has been leading Customer Adaptation Training (CAT) teams for adapting and customizing MGDS for the various operations and engineering teams. These CAT teams have typically consisted of only a few engineers who are familiar with operations and with the MGDS software and architecture. Our experience has provided a unique opportunity to work directly with the spacecraft and instrument operations teams and understand their requirements and how the MGDS can be adapted and customized to minimize their operations costs. As part of this work, we have developed workstation configurations, automation tools, and integrated user interfaces at minimal cost that have significantly improved productivity. We have also proved that these customized data systems are most successful if they are focused on the people and the tasks they perform and if they are based upon user confidence in the development team resulting from daily interactions. This paper will describe lessons learned in adapting JPL's MGDS to fly the Voyager, Galileo, and Mars Observer missions. We will explain how powerful, existing ground data systems can be adapted and packaged in a cost effective way for operations of small and large planetary missions. We will also describe how the MGDS was adapted to support operations within the Galileo Spacecraft Testbed. The Galileo testbed provided a unique opportunity to adapt MGDS to support command and control operations for a small autonomous operations team of a handful of engineers flying the Galileo Spacecraft flight system model.
Murphy, Susan C.↗
Inductive Learning Approaches for Improving Pilot Awareness of Aircraft Faults
Neural network flight controllers are able to accommodate a variety of aircraft control surface faults without detectable degradation of aircraft handling qualities. Under some faults, however, the effective flight envelope is reduced; this can lead to unexpected behavior if a pilot performs an action that exceeds the remaining control authority of the damaged aircraft. The goal of our work is to increase the pilot s situational awareness by informing him of the type of damage and resulting reduction in flight envelope. Our methodology integrates two inductive learning systems with novel visualization techniques. One learning system, the Inductive Monitoring System (IMS), learns to detect when a simulation includes faulty controls, while two others, Inductive Classification System (INCLASS) and multiple binary decision tree system (utilizing C4.5), determine the type of fault. In off-line training using only non-failure data, IMS constructs a characterization of nominal flight control performance based on control signals issued by the neural net flight controller. This characterization can be used to determine the degree of control augmentation required in the pitch, roll, and yaw command channels to counteract control surface failures. This derived information is typically sufficient to distinguish between the various control surface failures and is used to train both INCLASS and C4.5. Using data from failed control surface flight simulations, INCLASS and C4.5 independently discover and amplify features in IMS results that can be used to differentiate each distinct control surface failure situation. In real-time flight simulations, distinguishing features learned during training are used to classify control surface failures. Knowledge about the type of failure can be used by an additional automated system to alter its approach for planning tactical and strategic maneuvers. The knowledge can also be used directly to increase the pilot s situational awareness and inform manual maneuver decisions. Our multi-modal display of this information provides speech output to issue control surface failure warnings to a lesser-used communication channel and provides graphical displays with pilot-selectable !eve!s of details to issues additional information about the failure. We also describe a potential presentation for flight envelope reduction that can be viewed separately or integrated with an existing attitude indicator instrument. Preliminary results suggest that the inductive approach is capable of detecting that a control surface has failed and determining the type of fault. Furthermore, preliminary evaluations suggest that the interface discloses a concise summary of this information to the pilot.
Spikovska, Lilly↗
MARBLE: A Multi-GPU Aware Job Scheduler for Deep Learning on HPC Systems
Deep learning (DL) has become a key tool for solving complex scientific problems. However, managing the multi-dimensional large-scale data associated with DL, especially atop extant multiple graphics processing units (GPUs) in modern supercomputers poses significant challenges. Moreover, the latest high-performance computing (HPC) architectures bring different performance trends in training throughput compared to the existing studies. Existing DL optimizations such as larger batch size and GPU locality-aware scheduling have little effect on improving DL training throughput performance due to fast CPU-to-GPU connections. Additionally, DL training on multiple GPUs scales sublinearly. Thus, simply adding more GPUs to a system is ineffective. To this end, we design MARBLE, a first-of-its-kind job scheduler, which considers the non-linear scalability of GPUs at the intra-node level to schedule an appropriate number of GPUs per node for a job. By sharing the GPU resources on a node with multiple DL jobs, MARBLE avoids low GPU utilization in current multi-GPU DL training on HPC systems. Our comprehensive evaluation in the Summit supercomputer shows that MARBLE is able to improve DL training performance by up to 48.3% compared to the popular Platform Load Sharing Facility (LSF) scheduler. Compared to the state-of-the-art of DL scheduler, Optimus, MARBLE reduces the job completion time by up to 47%.
Han, Jingoo↗
Neural networks for self-learning control systems
It is shown how a neural network can learn of its own accord to control a nonlinear dynamic system. An emulator, a multilayered neural network, learns to identify the system's dynamic characteristics. The controller, another multilayered neural network, next learns to control the emulator. The self-trained controller is then used to control the actual dynamic system. The learning process continues as the emulator and controller improve and track the physical process. An example is given to illustrate these ideas. The 'truck backer-upper,' a neural network controller that steers a trailer truck while the truck is backing up to a loading dock, is demonstrated. The controller is able to guide the truck to the dock from almost any initial position. The technique explored should be applicable to a wide variety of nonlinear control problems.
Nguyen, Derrick H.↗
Evolving fuzzy rules in a learning classifier system
The fuzzy classifier system (FCS) combines the ideas of fuzzy logic controllers (FLC's) and learning classifier systems (LCS's). It brings together the expressive powers of fuzzy logic as it has been applied in fuzzy controllers to express relations between continuous variables, and the ability of LCS's to evolve co-adapted sets of rules. The goal of the FCS is to develop a rule-based system capable of learning in a reinforcement regime, and that can potentially be used for process control.
Valenzuela-Rendon, Manuel↗
NASA Crew Exploration Vehicle, Thermal Protection System, Lessons Learned
The Orion (CEV) thermal protection system (TPS) advanced development project (ADP) was initiated in late 2006 to reduce developmental risk by significant investment in multiple heat shield architectural solutions that can meet the needs both the Low Earth orbit (LEO) and Lunar return missions. At the same time, the CEV TPS ADP was also charged with developing a preliminary design for the heat shield to meet the PDR requirement and at the time of the PDR, transfer the design to Lockheed- Martin, the prime contractor. We reported on the developmental activities of the first 18 months at the IPPW5 in Bordeaux, France, last summer. In June 08, at the time of the IPPW6, the CEV TPS ADP would have nearly completed the preparation for the Orion PDR and would be close to the original three-year mark. We plan to report on the progress at the Atlanta workshop. In the past year, Orion TPS ADP investment in TPS Technology, especially in PICA ablative Heat-shield design, development, testing and engineering (DDTE) has paid off in enabling MSL mission to switch from SLA 561 V heat shield to PICA heat shield. CEV TPS ADP considered SLA 561 V as a candidate for LEO missions and our testing identified failure modes in SLA and as a result, we dropped SLA for further evaluation. This close synergy between two projects is a highly visible example of how investment in technology areas can and does benefit multiple missions. In addition, CEV TPS ADP has been able to revive the Apollo ablative system namely AVCOAT honeycomb architecture as an alternate to the baseline PICA architecture and we plan to report the progress we have made in AVCOAT. CEV TPS ADP has invested considerable resources in developing analytical models for PICA and AVCOAT, material property measurements that is essential to the design of the heat-shield, in arcjet testing, in understanding the differences between different arc jet facilities, namely NASA Ames, NASA JSC and Air Force's AEDC, and in Non-Destructive Evaluation (NDE), and in integration of and manufacturing heat shield as a system. The capabilities of the two heat shield systems including failure modes via testing and analysis, once established, can serve the Probe Community and future mission designers to inner and outer planetary exploration very well. For example, missions to Venus, Mars and Titan can use either one of the system by selecting the mission design parameters that utilizes the full characteristics of these system to make use of system efficiency that will result in reduced heat shield mass, system robustness that will enhance mission success and cost. We plan to present significant progresses of the past three years and highlight the significant contributions CEV TPS ADP Project has made to advance the state of the art in Thermal Protection System technology that has and will continue to benefit future entry probe missions.
NASA Crew Exploration Vehicle↗
Engineering Lessons Learned and Systems Engineering Applications
Systems Engineering is fundamental to good engineering, which in turn depends on the integration and application of engineering lessons learned and technical standards. Thus, good Systems Engineering also depends on systems engineering lessons learned from within the aerospace industry being documented and applied. About ten percent of the engineering lessons learned documented in the NASA Lessons Learned Information System are directly related to Systems Engineering. A key issue associated with lessons learned datasets is the communication and incorporation of this information into engineering processes. Systems Engineering has been defined (EINIS-632) as "an interdisciplinary approach encompassing the entire technical effort to evolve and verify an integrated and life-cycle balanced set of system people, product, and process solutions that satisfy customer needs". Designing reliable space-based systems has always been a goal for NASA, and many painful lessons have been learned along the way. One of the continuing functions of a system engineer is to compile development and operations "lessons learned" documents and ensure their integration into future systems development activities. They can produce insights and information for risk identification identification and characterization. on a new project. Lessons learned files from previous projects are especially valuable in risk
Gill, Paul S.↗
Machine Learning Reduced Order Model for Cost and Emission Assessment of a Pyrolysis System
Biomass pyrolysis is a promising approach for producing economic and environmentally-friendly fuels and bioproducts. Biomass pyrolysis experiments show that feedstock properties have a significant impact on product yields and composition. Scientists are developing detailed chemical reaction mechanisms to capture the relationships between biomass composition and pyrolysis yields. These mechanisms can be computationally intensive. In this study, we investigate the use of a machine learning reduced order model (ROM) for assessing the costs and emissions of a pyrolysis biorefinery. Here, we developed a Kriging-based ROM to predict pyrolysis yields of 314 feedstock samples based on the results of a detailed chemical kinetic pyrolysis mechanism. The ROM is integrated into a chemical process model for calculating mass and energy yields in a commercial-scale (2000 tonne/day) biorefinery. The ROM estimated biofuel yields of 65 to 130 gallons per ton of dry biomass. This results in biofuel minimum fuel-selling prices of $2.62 to $5.43 per gallon and emissions of -13.62 to 145 kg of CO 2 per MJ. The ROM achieved an average mean square error of 1.8e-20 and a mean absolute error of 0.53%. These results suggest that ROMs can facilitate rapid feedstock screening for biorefinery systems.
09 BIOMASS FUELS↗