Search NASA⌕ Search

SEARCH · Search NASA

Results for “intelligent control”

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 235 records · Page 13

The development of a Flight Test Engineer's Workstation for the Automated Flight Test Management System

The Automated Flight Test Management System (ATMS) is being developed as part of the NASA Aircraft Automation Program. This program focuses on the application of interdisciplinary state-of-the-art technology in artificial intelligence, control theory, and systems methodology to problems of operating and flight testing high-performance aircraft. The development of a Flight Test Engineer's Workstation (FTEWS) is presented, with a detailed description of the system, technical details, and future planned developments. The goal of the FTEWS is to provide flight test engineers and project officers with an automated computer environment for planning, scheduling, and performing flight test programs. The FTEWS system is an outgrowth of the development of ATMS and is an implementation of a component of ATMS on SUN workstations.

Tartt, David M.↗

Real-time diagnostics of the reusable rocket engine using on-line system identification

A model-based failure diagnosis system has been proposed for real-time diagnosis of SSME failures. Actuation, sensor, and system degradation failure modes are all considered by the proposed system. In the case of SSME actuation failures, it was shown that real-time identification can effectively be used for failure diagnosis purposes. It is a direct approach since it reduces the detection, isolation, and the estimation of the extent of the failures to the comparison of parameter values before and after the failure. As with any model-based failure detection system, the proposed approach requires a fault model that embodies the essential characteristics of the failure process. The proposed diagnosis approach has the added advantage that it can be used as part of an intelligent control system for failure accommodation purposes.

Guo, T.-H.↗

Hidden Markov model analysis of force/torque information in telemanipulation

A model for the prediction and analysis of sensor information recorded during robotic performance of telemanipulation tasks is presented. The model uses the hidden Markov model to describe the task structure, the operator's or intelligent controller's goal structure, and the sensor signals. A methodology for constructing the model parameters based on engineering knowledge of the task is described. It is concluded that the model and its optimal state estimation algorithm, the Viterbi algorithm, are very succesful at the task of segmenting the data record into phases corresponding to subgoals of the task. The model provides a rich modeling structure within a statistical framework, which enables it to represent complex systems and be robust to real-world sensory signals.

Hannaford, Blake↗

A real time neural net estimator of fatigue life

A neural network architecture is proposed to estimate, in real-time, the fatigue life of mechanical components, as part of the intelligent Control System for Reusable Rocket Engines. Arbitrary component loading values were used as input to train a two hidden-layer feedforward neural net to estimate component fatigue damage. The ability of the net to learn, based on a local strain approach, the mapping between load sequence and fatigue damage has been demonstrated for a uniaxial specimen. Because of its demonstrated performance, the neural computation may be extended to complex cases where the loads are biaxial or triaxial, and the geometry of the component is complex (e.g., turbopumps blades). The generality of the approach is such that load/damage mappings can be directly extracted from experimental data without requiring any knowledge of the stress/strain profile of the component. In addition, the parallel network architecture allows real-time life calculations even for high-frequency vibrations. Owing to its distributed nature, the neural implementation will be robust and reliable, enabling its use in hostile environments such as rocket engines.

Troudet, T.↗

Implementation of a model based fault detection and diagnosis for actuation faults of the Space Shuttle main engine

In a previous study, Guo, Merrill and Duyar, 1990, reported a conceptual development of a fault detection and diagnosis system for actuation faults of the space shuttle main engine. This study, which is a continuation of the previous work, implements the developed fault detection and diagnosis scheme for the real time actuation fault diagnosis of the space shuttle main engine. The scheme will be used as an integral part of an intelligent control system demonstration experiment at NASA Lewis. The diagnosis system utilizes a model based method with real time identification and hypothesis testing for actuation, sensor, and performance degradation faults.

Duyar, A.↗

Analysis of the Space Shuttle main engine simulation

This is a final report on an analysis of the Space Shuttle Main Engine Program, a digital simulator code written in Fortran. The research was undertaken in ultimate support of future design studies of a shuttle life-extending Intelligent Control System (ICS). These studies are to be conducted by NASA Lewis Space Research Center. The primary purpose of the analysis was to define the means to achieve a faster running simulation, and to determine if additional hardware would be necessary for speeding up simulations for the ICS project. In particular, the analysis was to consider the use of custom integrators based on the Matrix Stability Region Placement (MSRP) method. In addition to speed of execution, other qualities of the software were to be examined. Among these are the accuracy of computations, the useability of the simulation system, and the maintainability of the program and data files. Accuracy involves control of truncation error of the methods, and roundoff error induced by floating point operations. It also involves the requirement that the user be fully aware of the model that the simulator is implementing.

Deabreu-Garcia, J. Alex↗

Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Special approach/docking testcase results

As part of the RICIS project, the reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Maximum Mission (SMM) satellite simulation. In utilizing these fuzzy learning techniques, we use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use these two terms interchangeably to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS) and programming/testing support from other contractor personnel. This report is the final deliverable D4 in our milestones and project activity. It provides the test results for the special testcase of approach/docking scenario for the shuttle and SMM satellite. Based on our experience and analysis with the attitude and translational controllers, we have modified the basic configuration of the reinforcement learning algorithm in ARIC. The shuttle translational controller and its implementation in ARIC is described in our deliverable D3. In order to simulate the final approach and docking operations, we have set-up this special testcase as described in section 2. The ARIC performance results for these operations are discussed in section 3 and conclusions are provided in section 4 along with the summary for the project.

Jani, Yashvant↗

Uncertainty reasoning in expert systems

Intelligent control is a very successful way to transform the expert's knowledge of the type 'if the velocity is big and the distance from the object is small, hit the brakes and decelerate as fast as possible' into an actual control. To apply this transformation, one must choose appropriate methods for reasoning with uncertainty, i.e., one must: (1) choose the representation for words like 'small', 'big'; (2) choose operations corresponding to 'and' and 'or'; (3) choose a method that transforms the resulting uncertain control recommendations into a precise control strategy. The wrong choice can drastically affect the quality of the resulting control, so the problem of choosing the right procedure is very important. From a mathematical viewpoint these choice problems correspond to non-linear optimization and are therefore extremely difficult. In this project, a new mathematical formalism (based on group theory) is developed that allows us to solve the problem of optimal choice and thus: (1) explain why the existing choices are really the best (in some situations); (2) explain a rather mysterious fact that fuzzy control (i.e., control based on the experts' knowledge) is often better than the control by these same experts; and (3) give choice recommendations for the cases when traditional choices do not work.

Kreinovich, Vladik↗

Implementation of a model based fault detection and diagnosis technique for actuation faults of the SSME

In a previous study, Guo, Merrill and Duyar, 1990, reported a conceptual development of a fault detection and diagnosis system for actuation faults of the Space Shuttle main engine. This study, which is a continuation of the previous work, implements the developed fault detection and diagnosis scheme for the real time actuation fault diagnosis of the Space Shuttle Main Engine. The scheme will be used as an integral part of an intelligent control system demonstration experiment at NASA Lewis. The diagnosis system utilizes a model based method with real time identification and hypothesis testing for actuation, sensor, and performance degradation faults.

Duyar, A.↗

Symbolic discrete event system specification

Extending discrete event modeling formalisms to facilitate greater symbol manipulation capabilities is important to further their use in intelligent control and design of high autonomy systems. An extension to the DEVS formalism that facilitates symbolic expression of event times by extending the time base from the real numbers to the field of linear polynomials over the reals is defined. A simulation algorithm is developed to generate the branching trajectories resulting from the underlying nondeterminism. To efficiently manage symbolic constraints, a consistency checking algorithm for linear polynomial constraints based on feasibility checking algorithms borrowed from linear programming has been developed. The extended formalism offers a convenient means to conduct multiple, simultaneous explorations of model behaviors. Examples of application are given with concentration on fault model analysis.

Zeigler, Bernard P.↗

Acting to gain information: Real-time reasoning meets real-time perception

Recent advances in intelligent reactive systems suggest new approaches to the problem of deriving task-relevant information from perceptual systems in real time. The author will describe work in progress aimed at coupling intelligent control mechanisms to real-time perception systems, with special emphasis on frame rate visual measurement systems. A model for integrated reasoning and perception will be discussed, and recent progress in applying these ideas to problems of sensor utilization for efficient recognition and tracking will be described.

Rosenschein, Stan↗

Advances in polycrystalline thin-film photovoltaics for space applications

Polycrystalline, thin-film photovoltaics represent one of the few (if not the only) renewable power sources which has the potential to satisfy the demanding technical requirements for future space applications. The demand in space is for deployable, flexible arrays with high power-to-weight ratios and long-term stability (15-20 years). In addition, there is also the demand that these arrays be produced by scalable, low-cost, high yield, processes. An approach to significantly reduce costs and increase reliability is to interconnect individual cells series via monolithic integration. Both CIS and CdTe semiconductor films are optimum absorber materials for thin-film n-p heterojunction solar cells, having band gaps between 0.9-1.5 ev and demonstrated small area efficiencies, with cadmium sulfide window layers, above 16.5 percent. Both CIS and CdTe polycrystalline thin-film cells have been produced on a laboratory scale by a variety of physical and chemical deposition methods, including evaporation, sputtering, and electrodeposition. Translating laboratory processes which yield these high efficiency, small area cells into the design of a manufacturing process capable of producing 1-sq ft modules, however, requires a quantitative understanding of each individual step in the process and its (each step) effect on overall module performance. With a proper quantification and understanding of material transport and reactivity for each individual step, manufacturing process can be designed that is not 'reactor-specific' and can be controlled intelligently with the design parameters of the process. The objective of this paper is to present an overview of the current efforts at MMC to develop large-scale manufacturing processes for both CIS and CdTe thin-film polycrystalline modules. CIS cells/modules are fabricated in a 'substrate configuration' by physical vapor deposition techniques and CdTe cells/modules are fabricated in a 'superstrate configuration' by wet chemical methods. Both laser and mechanical scribing operations are used to monolithically integrate (series interconnect) the individual cells into modules. Results will be presented at the cell and module development levels with a brief description of the test methods used to qualify these devices for space applications. The approach and development efforts are directed towards large-scale manufacturability of established thin-film, polycrystalline processing methods for large area modules with less emphasis on maximizing small area efficiencies.

Lanning, Bruce R.↗

HyperCLIPS: A HyperCard interface to CLIPS

HyperCLIPS combines the intuitive, interactive user interface of the Apple Macintosh(TM) with the powerful symbolic computation of an expert system interpreter. HyperCard(TM) is an excellent environment for quickly developing the front end of an application with buttons, dialogs, and pictures, while the CLIPS interpreter provides a powerful inference engine for complex problem solving and analysis. By integrating HyperCard and CLIPS the advantages and uses of both packages are made available for a wide range of uses: rapid prototyping of knowledge-based expert systems, interactive simulations of physical systems, and intelligent control of hypertext processes, to name a few. Interfacing HyperCard and CLIPS is natural. HyperCard was designed to be extended through the use of external commands (XCMDs), and CLIPS was designed to be embedded through the use of the I/O router facilities and callable interface routines. With the exception of some technical difficulties which will be discussed later, HyperCLIPS implements this interface in a straight forward manner, using the facilities provided. An XCMD called 'ClipsX' was added to HyperCard to give access to the CLIPS routines: clear, load, reset, and run. And an I/O router was added to CLIPS to handle the communication of data between CLIPS and HyperCard.

Pickering, Brad↗

FDEMS Sensing for Automated Intelligent Processing of PMR-15

The purpose of this grant was to develop frequency dependent dielectric measurements, often called FDEMS (frequency dependent electromagnetic sensing), to monitor and intelligently control the cure process in PMR-15, a stoichiometric mixture of a nadic ester, dimethyl ester, and methylendianiline in a monomor ratio.

Kranbuehl, David E.↗

FAA/NASA Joint University Program for Air Transportation Research 1994-1995

The Joint University Program for Air Transportation Research (JUP) is a coordinated set of three grants co-sponsored by the Federal Aviation Administration (FAA) and the National Aeronautics and Space Administration (NASA). Under JUP, three institutions: the Massachusetts Institute of Technology, Princeton, and Ohio Universities receive research grants and collaborate with FAA and NASA in defining and performing civil aeronautics research in a multitude of areas. Some of these disciplines are artificial intelligence, control theory, atmospheric hazards, navigation, avionics, human factors, flight dynamics, air traffic management, and electronic communications.

NASA PROGRAMS↗

Cascade Error Projection with Low Bit Weight Quantization for High Order Correlation Data

In this paper, we reinvestigate the solution for chaotic time series prediction problem using neural network approach. The nature of this problem is such that the data sequences are never repeated, but they are rather in chaotic region. However, these data sequences are correlated between past, present, and future data in high order. We use Cascade Error Projection (CEP) learning algorithm to capture the high order correlation between past and present data to predict a future data using limited weight quantization constraints. This will help to predict a future information that will provide us better estimation in time for intelligent control system. In our earlier work, it has been shown that CEP can sufficiently learn 5-8 bit parity problem with 4- or more bits, and color segmentation problem with 7- or more bits of weight quantization. In this paper, we demonstrate that chaotic time series can be learned and generalized well with as low as 4-bit weight quantization using round-off and truncation techniques. The results show that generalization feature will suffer less as more bit weight quantization is available and error surfaces with the round-off technique are more symmetric around zero than error surfaces with the truncation technique. This study suggests that CEP is an implementable learning technique for hardware consideration.

Duong, Tuan A.↗

A New Look at NASA: Strategic Research In Information Technology

This viewgraph presentation provides information on research undertaken by NASA to facilitate the development of information technologies. Specific ideas covered here include: 1) Bio/nano technologies: biomolecular and nanoscale systems and tools for assembly and computing; 2) Evolvable hardware: autonomous self-improving, self-repairing hardware and software for survivable space systems in extreme environments; 3) High Confidence Software Technologies: formal methods, high-assurance software design, and program synthesis; 4) Intelligent Controls and Diagnostics: Next generation machine learning, adaptive control, and health management technologies; 5) Revolutionary computing: New computational models to increase capability and robustness to enable future NASA space missions.

Alfano, David↗

Beyond the Prototype: The Design Evolution of a Deployed AI System

Our previous experiences with deployed intelligent control agents for NASA advanced life support systems (Schreckenghost et al., 2002) inspired us to develop the Distributed Collaboration and Interaction (DCI) system to help humans and mostly-autonomous software agents work together. We discovered many unaddressed needs for human interaction with control agents that operate continuously over months to years to monitor and perform process control for regenerative life support systems. These systems recover usable water or air from the waste products created by biological systems over time. Through the DCI project, we have addressed the needs for interaction between humans and autonomous control systems. This paper describes the software engineering aspects of our experiences, first, in designing and developing a prototype of the DCI system, and later, in adjusting the implementation to make the leap from initial prototype to a system ready to be applied under varying circumstances to meet different needs. The details in the paper focus primarily on the second stage of development. The DCI system is currently deployed, operating 24/7, to assist humans to interact with an advanced Water Recovery System (WRS). In addition, we have demonstrated an application of DCI to support ground personnel in mission support roles.

Martin, C.↗