Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning based 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.

At least 163 records · Page 9

MITT writer and MITT writer advanced development: Developing authoring and training systems for complex technical domains

MITT Writer is a software system for developing computer based training for complex technical domains. A training system produced by MITT Writer allows a student to learn and practice troubleshooting and diagnostic skills. The MITT (Microcomputer Intelligence for Technical Training) architecture is a reasonable approach to simulation based diagnostic training. MITT delivers training on available computing equipment, delivers challenging training and simulation scenarios, and has economical development and maintenance costs. A 15 month effort was undertaken in which the MITT Writer system was developed. A workshop was also conducted to train instructors in how to use MITT Writer. Earlier versions were used to develop an Intelligent Tutoring System for troubleshooting the Minuteman Missile Message Processing System.

Wiederholt, Bradley J.↗

Another Approach to Enhance Airline Safety: Using Management Safety Tools

The ultimate goal of conducting an accident investigation is to prevent similar accidents from happening again and to make operations safer system-wide. Based on the findings extracted from the investigation, the "lesson learned" becomes a genuine part of the safety database making risk management available to safety analysts. The airline industry is no exception. In the US, the FAA has advocated the usage of the System Safety concept in enhancing safety since 2000. Yet, in today s usage of System Safety, the airline industry mainly focuses on risk management, which is a reactive process of the System Safety discipline. In order to extend the merit of System Safety and to prevent accidents beforehand, a specific System Safety tool needs to be applied; so a model of hazard prediction can be formed. To do so, the authors initiated this study by reviewing 189 final accident reports from the National Transportation Safety Board (NTSB) covering FAR Part 121 scheduled operations. The discovered accident causes (direct hazards) were categorized into 10 groups Flight Operations, Ground Crew, Turbulence, Maintenance, Foreign Object Damage (FOD), Flight Attendant, Air Traffic Control, Manufacturer, Passenger, and Federal Aviation Administration. These direct hazards were associated with 36 root factors prepared for an error-elimination model using Fault Tree Analysis (FTA), a leading tool for System Safety experts. An FTA block-diagram model was created, followed by a probability simulation of accidents. Five case studies and reports were provided in order to fully demonstrate the usefulness of System Safety tools in promoting airline safety.

Lu, Chien-tsug↗

Watch what you say, your computer might be listening: A review of automated speech recognition

Spoken language is the most convenient and natural means by which people interact with each other and is, therefore, a promising candidate for human-machine interactions. Speech also offers an additional channel for hands-busy applications, complementing the use of motor output channels for control. Current speech recognition systems vary considerably across a number of important characteristics, including vocabulary size, speaking mode, training requirements for new speakers, robustness to acoustic environments, and accuracy. Algorithmically, these systems range from rule-based techniques through more probabilistic or self-learning approaches such as hidden Markov modeling and neural networks. This tutorial begins with a brief summary of the relevant features of current speech recognition systems and the strengths and weaknesses of the various algorithmic approaches.

Degennaro, Stephen V.↗

PDA: A coupling of knowledge and memory for case-based reasoning

Problem solving in most domains requires reference to past knowledge and experience whether such knowledge is represented as rules, decision trees, networks or any variant of attributed graphs. Regardless of the representational form employed, designers of expert systems rarely make a distinction between the static and dynamic aspects of the system's knowledge base. The current paper clearly distinguishes between knowledge-based and memory-based reasoning where the former in its most pure sense is characterized by a static knowledge based resulting in a relatively brittle expert system while the latter is dynamic and analogous to the functions of human memory which learns from experience. The paper discusses the design of an advisory system which combines a knowledge base consisting of domain vocabulary and default dependencies between concepts with a dynamic conceptual memory which stores experimental knowledge in the form of cases. The case memory organizes past experience in the form of MOPs (memory organization packets) and sub-MOPs. Each MOP consists of a context frame and a set of indices. The context frame contains information about the features (norms) common to all the events and sub-MOPs indexed under it.

Bharwani, S.↗

Optimization of low gravity materials processing experiments using expert systems

The use of an expert system for the control of materials processing experiments in a facility such as the Space Station provides a number of attractive features for insuring that certain critical process parameters can be used to optimize the productivity of the materials processing experiments. The proposed approach to implementation of an expert system utilizes a knowledge base of desired process characteristics which will provide the desired results. The knowledge base for each experiment will be created in conjunction with the scientific investigator in charge of the experiment. Improvements to the knowledge base will be expanded to include self learning sessions in ground based experiments in order to teach the expert system how to respond to perturbations in the process and update the knowledge base on what process change should be implemented in order to reach the desired end product. Design considerations using an on-line real time expert system such as PICON is studied. The types of experiments evaluated include several types of solidification experiments which will be performed on the Space Station.

Workman, Gary L.↗

Hybrid Motion Planning with Multiple Destinations

In our initial proposal, we laid plans for developing a hybrid motion planning system that combines the concepts of visibility-based motion planning, artificial potential field based motion planning, evolutionary constrained optimization, and reinforcement learning. Our goal was, and still is, to produce a hybrid motion planning system that outperforms the best traditional motion planning systems on problems with dynamic environments. The proposed hybrid system will be in two parts the first is a global motion planning system and the second is a local motion planning system. The global system will take global information about the environment, such as the placement of the obstacles and goals, and produce feasible paths through those obstacles. We envision a system that combines the evolutionary-based optimization and visibility-based motion planning to achieve this end.

Clouse, Jeffery↗

Applicability of Loads Estimation Techniques Using Sparse Acceleration Sensor Data to Spacecraft Structural Health Monitoring

The use of structural health monitoring systems on spacecraft structures can play a crucial role in ensuring the safety, reliability, and longevity of the structure by gathering and analyzing onboard sensor data. Of specific importance is monitoring for excessive loading at critical interfaces as any off-nominal structural excitations experienced by spacecraft structures can cause early unpredicted high structural life consumption or damage. The availability and cost of flight-certified sensors along with the size of spacecraft structures and allowable payload mass drives the need for a method to estimate loads using sparsely-located sensors. Numerous approaches such as physics-based, statistical learning, and physics-enhanced statistical learning algorithms have gained popularity among structural prognostics applications. However, developing noise-robust prediction models to assess loads and structural life predictions from a sparse multi-sensor data acquisition system can be a challenging task. This paper discusses the evaluation of physics-based versus machine-learning algorithms for predicting loads and structural life at mission critical locations on the spacecraft structure using a finite element loads analysis with the application of simulated noise and noise reduction techniques. To estimate the loads from accelerations, the physics-based algorithm leverages a loads transformation matrix from a Craig-Bampton reduced finite element model. A System Equivalent Reduction Expansion Process (SEREP) and a pseudo-inverse approach are considered to expand from the onboard sensor degrees of freedom to the Craig-Bampton model degrees of freedom. The machine learning algorithm provides a data driven solution/mapping of the sensor accelerations to the loads at the mission critical locations using a high dimensionality analysis. Although these strategies produce comparable loads prediction without noise, the limitations of these strategies with incorporating simulated noise and noise reduction techniques with low signal to noise ratio signals are evaluated. The study demonstrates the immense potential of statistical learning algorithms for sparse structural prognostic models and enhancing signal denoising techniques. These findings also highlight the need for noise-resilient prognostic models and low-noise data acquisition systems onboard spacecraft structures.

Spacecraft Structural Health Monitoring↗

The Pacor 2 expert system: A case-based reasoning approach to troubleshooting

The Packet Processor 2 (Pacor 2) Data Capture Facility (DCF) acquires, captures, and performs level-zero processing of packet telemetry for spaceflight missions that adhere to communication services recommendations established by the Consultative Committee for Space Data Systems (CCSDS). A major goal of this project is to reduce life-cycle costs. One way to achieve this goal is to increase automation. Through automation, using expert systems, and other technologies, staffing requirements will remain static, which will enable the same number of analysts to support more missions. Analysts provide packet telemetry data evaluation and analysis services for all data received. Data that passes this evaluation is forwarded to the Data Distribution Facility (DDF) and released to scientists. Through troubleshooting, data that fails this evaluation is dumped and analyzed to determine if its quality can be improved before it is released. This paper describes a proof-of-concept prototype that troubleshoots data quality problems. The Pacor 2 expert system prototype uses the case-based reasoning (CBR) approach to development, an alternative to a rule-based approach. Because Pacor 2 is not operational, the prototype has been developed using cases that describe existing troubleshooting experience from currently operating missions. Through CBR, this experience will be available to analysts when Pacor 2 becomes operational. As Pacor 2 unique experience is gained, analysts will update the case base. In essence, analysts are training the system as they learn. Once the system has learned the cases most likely to recur, it can serve as an aide to inexperienced analysts, a refresher to experienced analysts for infrequently occurring problems, or a training tool for new analysts. The Expert System Development Methodology (ESDM) is being used to guide development.

Sary, Charisse↗

Constraint-Based Scheduling System

Report describes continuing development of software for constraint-based scheduling system implemented eventually on massively parallel computer. Based on machine learning as means of improving scheduling. Designed to learn when to change search strategy by analyzing search progress and learning general conditions under which resource bottleneck occurs.

Zweben, Monte↗

On Automating Failure Mode Analysis and Enforcing its Integrity

This paper reports our experience on the development of a design-for-safety (DFS) workbench called Risk Assessment and Management Environment (RAME) for microelectronic avionics systems. Our objective is to transform DFS practice from an ad-hoc, inefficient, error-prone approach to a stringent engineering process such that DFS can keep up with the rapidly growing complexity of avionics systems. In particular, RAME is built upon an information infrastructure that comprises a fault model, a knowledge base, and a failure reporting/tracking system. This infrastructure permits systematic learning from prior projects and enables the automation of failure modes, effects and criticality analysis (FMECA). Among other unique features, the most important advantage of RAME is its capability of directly accepting design source code in hardware description languages (HDLs) for automated failure mode analysis, which enables RAME to be compatible and to evolve with most electronic-computer-aided-design systems. Through an initial experimental evaluation of the RAME prototype, we show that our approach to FMECA automation improves failure mode analysis turn-around-time, completeness, and accuracy.

design for safety↗

Image Mapping and Visual Attention on the Sensory Ego-Sphere

The Sensory Ego-Sphere (SES) is a short-term memory for a robot in the form of an egocentric, tessellated, spherical, sensory-motor map of the robot s locale. Visual attention enables fast alignment of overlapping images without warping or position optimization, since an attentional point (AP) on the composite typically corresponds to one on each of the collocated regions in the images. Such alignment speeds analysis of the multiple images of the area. Compositing and attention were performed two ways and compared: (1) APs were computed directly on the composite and not on the full-resolution images until the time of retrieval; and (2) the attentional operator was applied to all incoming imagery. It was found that although the second method was slower, it produced consistent and, thereby, more useful APs. The SES is an integral part of a control system that will enable a robot to learn new behaviors based on its previous experiences, and that will enable it to recombine its known behaviors in such a way as to solve related, but novel, task problems with apparent creativity. The approach is to combine sensory-motor data association and dimensionality reduction to learn navigation and manipulation tasks as sequences of basic behaviors that can be implemented with a small set of closed-loop controllers. Over time, the aggregate of behaviors and their transition probabilities form a stochastic network. Then given a task, the robot finds a path in the network that leads from its current state to the goal. The SES provides a short-term memory for the cognitive functions of the robot, association of sensory and motor data via spatio-temporal coincidence, direction of the attention of the robot, navigation through spatial localization with respect to known or discovered landmarks, and structured data sharing between the robot and human team members, the individuals in multi-robot teams, or with a C3 center.

Fleming, Katherine Achim↗

Open-source Techniques for Automated Landslide Inventory Generation for Rapid Response

Manual mapping is the most used method for generating landslide inventories. For rapid response scenario this method becomes tedious and time consuming. The Landslide team at NASA Goddard Space Flight Center has been developing open-source landslide mapping systems for rapid generation of landslide inventories. We have developed a Python-based landslide mapping framework known as the Semi-Automatic Landslide Detection (SALaD) system that uses Object-based Image Analysis and machine learning. For production of event-based inventories, SALaD was modified to include a change detection module (SALaD-CD). Utilizing high-resolution imagery form from Planet and Maxar, we have generated multiple rapid response landslide inventories that have been used by emergency responders on the ground, the NASA Disasters program, and academia. Currently, we are exploiting deep learning frameworks for landslide mapping. We are interested to learn about efficient way to harmonize multi-sensor data for creating a long-term record of landslides, training strategies and ongoing deep learning-based efforts for natural hazard characterization within NASA and UMD.

Pukar Amatya↗

Accelerated Simulation of Air Pollution Using NVIDIA RAPIDS

Atmospheric chemistry models are a central tool to study and forecast the impact of air pollution on the environment, vegetation, and human health. However, the numerical simulation of chemical kinetics is computationally expensive due to the stiffness of the system of ordinary differential equations that describes atmospheric chemistry. Here we present an alternative approach to the computation of atmospheric chemistry based on machine learning. Our training data set is produced using the NASA Goddard Earth Observing System (GEOS) model with GEOS-Chem chemistry, run on the NASA Center for Climate Simulation (NCCS) Discover supercomputing cluster on 384 Intel Xeon Haswell cores. This model spends more than 50% of total run time on solving atmospheric chemistry. The data set contains as input features the air pollution concentrations before solving the differential equations, together with some key physical parameters such as temperature and sun intensity. As target variables we define the air pollution concentrations after solving the differential equations. Using Dask-cuDF and Dask-XGBoost on the NVIDIA RAPIDS platform on 8 Tesla V100 GPUs, we generate from this training set gradient boosted decision tree models that can reproduce the simulation of chemical kinetics. We do this on the NCCS Advanced Data Analytics Platform (ADAPT) science cloud environment. Our application takes full advantage of recent advances in Dask-XGBoost, such as multi-node and multi-GPU scaling for distributed training with large data sets. The increase in training data size enabled by this is critical to capture the full range of chemical environments encountered across the globe and all annual seasons.The boosted tree models offer good predictability and show many of the features of the full chemistry reference simulation. Further improvements can be achieved through mass balance considerations and by accounting for error correlations. We incorporate the boosted tree models into the GEOS reference model using XGBoost's C API. This enables a seamless integration of the GPU trained models into GEOS-Chem, which is written in Fortran and optimized for use in a massively parallel CPU environment. We show the benefits of this approach and discuss the potential speedup of this machine learning accelerated atmospheric chemistry model.

Keller, Christoph A.↗

CyberGAN: Generating High-fidelity Cybersecurity Data With Generative Adversarial Networks

Machine learning for cyber defense offers the promise of detecting adversarial activity against the ground data systems managing critical space assets. A fundamental challenge facing machine learning research in cybersecurity is the lack of high-fidelity, shareable datasets for robust evaluation and testing of machine learning-based solutions. High-fidelity, real-world datasets are necessary for reliable benchmarking of nominal system behavior and malicious activity. Unfortunately, such realistic datasets of both nominal and adversarial activity are rarely shared publicly by data owners due to security and privacy concerns. Besides, the available adversarial data is sparse, which makes training models on malicious activity much harder. This situation has impeded and continues to impede the research and successful adoption of machine learning methods for cyber defense. Researchers have dealt with this problem by generating data within a low-fidelity lab environment, using classified and thus unshareable datasets, or downloading low-fidelity public datasets made available by others. We propose an innovative solution to the problem by employing machine learning methods to generate high-fidelity data. Specifically, we propose the use of Generative Adversarial Networks (GANs) to generate high-fidelity data for cybersecurity purposes. GANs have found successful image processing and natural language applications, but have not yet been investigated for cyber data generation. Our proposed approach first involves training the `discriminator' network of the GAN with a sample of real-world data consisting of malicious and nominal samples. We then use the `generator' network to generate new high-fidelity data samples consisting of an appropriate mix of malicious and nominal activity. We demonstrate applications of our architecture by generating high-fidelity cybersecurity data containing both malicious and nominal samples. We thoroughly evaluate the fidelity of our generated data using heuristics and evaluate its usefulness for machine learning applications using three different datasets. Overall, our approach results in high-fidelity, shareable datasets.

Zhang, Yuening↗

On the recognition of complex structures: Computer software using artificial intelligence applied to pattern recognition

An approach to simultaneous interpretation of objects in complex structures so as to maximize a combined utility function is presented. Results of the application of a computer software system to assign meaning to regions in a segmented image based on the principles described in this paper and on a special interactive sequential classification learning system, which is referenced, are demonstrated.

Yakimovsky, Y.↗

Update on Feasibility of UV LEDs in a Spacecraft Wastewater Application

As the National Aeronautics and Space Administration (NASA) expands its scope and begins to venture into long-duration, manned space flights, the function and maintenance of spacecraft water systems becomes increasingly critical and difficult. New mission requirements limit opportunities for resupply and demand extended periods of uncrewed operations. Based on lessons learned from the International Space Station (ISS), one particular challenge of future spacecraft water systems will be maintaining adequate microbial control, especially in water subsystems and component-level elements, where effective long-duration biocontrol strategies do not currently exist. To ensure the reliability and redundancy in these systems, innovative technologies will be needed to ensure mission success. After proving feasibility of commercial-off-the-shelf (COTS) devices in flow-through applications in 2018, work focused on utilizing ultraviolet (UV) light emitting diodes (LEDs) in a wastewater tank application. This paper gives an update on the tank testing that has been performed to date. Using this technology may reduce the need for consumable resupply, such as filters or biocides, and minimize crew time to make the repairs on exhausted and/or compromised systems. The ultimate rationale behind developing a UV disinfection system is to increase the stability of water systems as requirements for sterility and microbial control become more stringent for deep space missions. The resulting data from this study will be used to narrow down possible technology demonstrations for selected ISS locations to assess the use of UV technology on future exploration-class spacecraft systems.

Susan N. Gilbert↗

Advanced Oxygen Generation Assembly for Exploration Missions

Future Exploration missions will require an Oxygen Generation Assembly (OGA) to electrolyze water to supply oxygen for crew metabolic consumption. The system design will be based on the International Space Station (ISS) OGA but with added improvements based on lessons learned during ISS operations and technological advances since the original OGA was designed and built. These improvements will reduce system weight, crew maintenance time and spares mass while increasing reliability. Currently, the design team is investigating the feasibility of the upgrades by performing ground tests and analyses. Upgrades being considered include: redesign of the electrolysis cell stack, deletion of the hydrogen dome, replacement of the hydrogen sensors, deletion of the wastewater interface, redesign of the recirculation loop deionizing bed and redesign of the cell stack Power Supply Module. The upgrades will be first demonstrated on the ISS OGA.

Takada, Kevin↗

A Model-Based Expert System for Space Power Distribution Diagnostics

When engineers diagnose system failures, they often use models to confirm system operation. This concept has produced a class of advanced expert systems that perform model-based diagnosis. A model-based diagnostic expert system for the Space Station Freedom electrical power distribution test bed is currently being developed at the NASA Lewis Research Center. The objective of this expert system is to autonomously detect and isolate electrical fault conditions. Marple, a software package developed at TRW, provides a model-based environment utilizing constraint suspension. Originally, constraint suspension techniques were developed for digital systems. However, Marple provides the mechanisms for applying this approach to analog systems such as the test bed, as well. The expert system was developed using Marple and Lucid Common Lisp running on a Sun Sparc-2 workstation. The Marple modeling environment has proved to be a useful tool for investigating the various aspects of model-based diagnostics. This report describes work completed to date and lessons learned while employing model-based diagnostics using constraint suspension within an analog system.

Quinn, Todd M.↗