Friction Stir Welding Controls Using Machine Learning
Explore the source record for details and available documents.
Scott B Tashakkor↗
SEARCH · Search NASA
Results for “learning 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.
Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Translational controller results
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 also use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use two terms interchangeable to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS). This report is the deliverable D3 in our project activity and provides the test results of the fuzzy learning translational controller. This report is organized in six sections. Based on our experience and analysis with the attitude controller, we have modified the basic configuration of the reinforcement learning algorithm in ARIC as described in section 2. The shuttle translational controller and its implementation in fuzzy learning architecture is described in section 3. Two test cases that we have performed are described in section 4. Our results and conclusions are discussed in section 5, and section 6 provides future plans and summary for the project.
Jani, Yashvant↗
Active controllers and the time duration to learn a task
An active controller was used to help train naive subjects involved in a compensatory tracking task. The controller is called active in this context because it moves the subject's hand in a direction to improve tracking. It is of interest here to question whether the active controller helps the subject to learn a task more rapidly than the passive controller. Six subjects, inexperienced to compensatory tracking, were run to asymptote root mean square error tracking levels with an active controller or a passive controller. The time required to learn the task was defined several different ways. The results of the different measures of learning were examined across pools of subjects and across controllers using statistical tests. The comparison between the active controller and the passive controller as to their ability to accelerate the learning process as well as reduce levels of asymptotic tracking error is reported here.
Repperger, D. W.↗
Online Control Design for Learn-To-Fly
Two methods were developed for online control design as part of a flight test e ort to examine the feasibility of the NASA Learn-to-Fly concept. The methods use an aerodynamic model of the aircraft that is being identified in real-time onboard the aircraft to adjust the control parameters. One method employs adaptive nonlinear dynamic inversion, whereas the other consists of a classical autopilot structure. E ects from the interaction between the realtime modeling and the developed control laws are discussed. The Learn-to-Fly concept has been deemed feasible based on successful flights of both a stable and unstable aircraft.
Snyder, Steven M↗
Autonomous Spacecraft Attitude Control Using Deep Reinforcement Learning
While machine learning and spacecraft autonomy continue to gain research interest, significant work remains to be done in efficiently applying modern machine learning techniques to problems in space ight. This study presents a framework for deriving a discrete neural spacecraft attitude controller using reinforcement learning, a paradigm of machine learning, without the need for high-performance computing. The developed attitude controller is an approximately time-optimal solution to a highly constrained control problem, able to achieve well above industry-standard pointing accuracies. Control examples are also presented of the agent performing large-angle spacecraft slews in the developed simulation environment and future extensions of this work are discussed.
ATAP↗
Brain-Computer Interfaces for 1-D and 2-D Cursor Control: Designs Using Volitional Control of the EEG Spectrum or Steady-State Visual Evoked Potentials
We have developed and tested two EEG-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target Practice, is a system for one-dimensional device control, in which participants use biofeedback to learn voluntary control of their EEG spectra. Target Practice uses a KF LS classifier to map power spectra of 30-electrode EEG signals to rightward or leftward position of a moving cursor on a computer display. Three subjects learned to control motion of a cursor on a video display in multiple blocks of 60 trials over periods of up to six weeks. The best subject s average skill in correct selection of the cursor direction grew from 58% to 88% after 13 training sessions. Target Practice also implements online control of two artifact sources: a) removal of ocular artifact by linear subtraction of wavelet-smoothed vertical and horizontal EOG signals, b) control of muscle artifact by inhibition of BCI training during periods of relatively high power in the 40-64 Hz band. The second BCI, Think Pointer, is a system for two-dimensional cursor control. Steady-state visual evoked potentials (SSVEP) are triggered by four flickering checkerboard stimuli located in narrow strips at each edge of the display. The user attends to one of the four beacons to initiate motion in the desired direction. The SSVEP signals are recorded from eight electrodes located over the occipital region. A KPLS classifier is individually calibrated to map multichannel frequency bands of the SSVEP signals to right-left or up-down motion of a cursor on a computer display. The display stops moving when the user attends to a central fixation point. As for Target Practice, Think Pointer also implements wavelet-based online removal of ocular artifact; however, in Think Pointer muscle artifact is controlled via adaptive normalization of the SSVEP. Training of the classifier requires about three minutes. We have tested our system in real-time operation in three human subjects. Across subjects and sessions, control accuracy ranged from 80% to 100% correct with lags of 1-5 seconds for movement initiation and turning.
Trejo, Leonard J.↗
Space Station Control Moment Gyroscope Lessons Learned
Four 4760 Nms (3510 ft-lbf-s) Double Gimbal Control Moment Gyroscopes (DGCMG) with unlimited gimbal freedom about each axis were adopted by the International Space Station (ISS) Program as the non-propulsive solution for continuous attitude control. These CMGs with a life expectancy of approximately 10 years contain a flywheel spinning at 691 rad/s (6600 rpm) and can produce an output torque of 258 Nm (190 ft-lbf)1. One CMG unexpectedly failed after approximately 1.3 years and one developed anomalous behavior after approximately six years. Both units were returned to earth for failure investigation. This paper describes the Space Station Double Gimbal Control Moment Gyroscope design, on-orbit telemetry signatures and a summary of the results of both failure investigations. The lessons learned from these combined sources have lead to improvements in the design that will provide CMGs with greater reliability to assure the success of the Space Station. These lessons learned and design improvements are not only applicable to CMGs but can be applied to spacecraft mechanisms in general.
Gurrisi, Charles↗
A reinforcement learning-based architecture for fuzzy logic control
This paper introduces a new method for learning to refine a rule-based fuzzy logic controller. A reinforcement learning technique is used in conjunction with a multilayer neural network model of a fuzzy controller. The approximate reasoning based intelligent control (ARIC) architecture proposed here learns by updating its prediction of the physical system's behavior and fine tunes a control knowledge base. Its theory is related to Sutton's temporal difference (TD) method. Because ARIC has the advantage of using the control knowledge of an experienced operator and fine tuning it through the process of learning, it learns faster than systems that train networks from scratch. The approach is applied to a cart-pole balancing system.
Berenji, Hamid R.↗
Reinforcement Learning Approach to Flight Control Allocation with Distributed Electric Propulsion
The flight control system of the SUSAN Electrofan concept aircraft achieves attitude control using both conventional flight control surfaces and differential thrust through distributed electric propulsion (DEP) from sixteen wing-mounted electric engines. The introduction of eight pairs of wing fans for attitude control creates a highly actuated system. Such a system requires more sophisticated control to operate, especially in the presence of wingfan failures where the loss of a single wingfan can result in a thrust imbalance. This paper investigates the use of deep reinforcement learning (RL) using proximal policy optimization (PPO) to achieve attitude control through a combination of DEP and control surface deflections. First, the paper examines the aircraft undergoing a coordinated turn. Then, it examines the aircraft experiencing a wingfan failure during cruise conditions. It is shown that deep reinforcement learning can be a potential avenue for nonlinear flight control design.
Distributed Electric Propulsion↗
Fuzzy Adaptive Control for Intelligent Autonomous Space Exploration Problems
The principal objective of the research reported here is the re-design, analysis and optimization of our newly developed neural network fuzzy adaptive controller model for complex processes capable of learning fuzzy control rules using process data and improving its control through on-line adaption. The learned improvement is according to a performance objective function that provides evaluative feedback; this performance objective is broadly defined to meet long-range goals over time. Although fuzzy control had proven effective for complex, nonlinear, imprecisely-defined processes for which standard models and controls are either inefficient, impractical or cannot be derived, the state of the art prior to our work showed that procedures for deriving fuzzy control, however, were mostly ad hoc heuristics. The learning ability of neural networks was exploited to systematically derive fuzzy control and permit on-line adaption and in the process optimize control. The operation of neural networks integrates very naturally with fuzzy logic. The neural networks which were designed and tested using simulation software and simulated data, followed by realistic industrial data were reconfigured for application on several platforms as well as for the employment of improved algorithms. The statistical procedures of the learning process were investigated and evaluated with standard statistical procedures (such as ANOVA, graphical analysis of residuals, etc.). The computational advantage of dynamic programming-like methods of optimal control was used to permit on-line fuzzy adaptive control. Tests for the consistency, completeness and interaction of the control rules were applied. Comparisons to other methods and controllers were made so as to identify the major advantages of the resulting controller model. Several specific modifications and extensions were made to the original controller. Additional modifications and explorations have been proposed for further study. Some of these are in progress in our laboratory while others await additional support. All of these enhancements will improve the attractiveness of the controller as an effective tool for the on line control of an array of complex process environments.
Esogbue, Augustine O.↗
Thermoelectric Converter for Loop Heat Pipe Temperature Control: Experience and Lessons Learned
This paper describes the theoretical background and implementation methodology of using a thermoelectric converter (TEC) for operating temperature control of a loop heat pipe (LHP). In particular, experimental results from ambient and thermal vacuum tests of an LHP are presented for illustrations. The most commonly used state-of-the-art method to control the LHP operating temperature is to cold bias its compensation chamber (CC) and use an electrical heater to maintain the CC at the desired set point temperature. Although effective, this approach has its shortcomings in that the electrical heater can only provide heating to the CC, and the required power can be large under certain conditions. An alternative method is to use a TEC, which is capable of providing both heating and cooling to the CC. In this method, one side of the TEC is attached to the CC, and the other side is connected to the evaporator via a thermal strap. Using a bipolar power supply and a control algorithm, a TEC can function as a heater or a cooler, depending on the direction of the current flow. Extensive ground tests of several LHPs have demonstrated that a TEC can provide very tight temperature control for the CC. It also offers several additional advantages: (1) The LHP can operate at temperatures below its natural operating temperature at low heat loads; (2) The required heater power for a TEC is much less than that for an electrical heater; and (3) It enhances the LHP start-up success. Although the concept of using a TEC for LHP temperature control is simple, there are many factors to be considered in its implementation for space applications because the TEC is susceptible to the shear stress and yet has to sustain the dynamic load under the spacecraft launch environment. The added features that help the TEC to withstand the dynamic load will inevitably affect the TEC thermal performance. Some experiences and lessons learned are addressed in this paper.
Ku, Jentung↗
On the integration of reinforcement learning and approximate reasoning for control
The author discusses the importance of strengthening the knowledge representation characteristic of reinforcement learning techniques using methods such as approximate reasoning. The ARIC (approximate reasoning-based intelligent control) architecture is an example of such a hybrid approach in which the fuzzy control rules are modified (fine-tuned) using reinforcement learning. ARIC also demonstrates that it is possible to start with an approximately correct control knowledge base and learn to refine this knowledge through further experience. On the other hand, techniques such as the TD (temporal difference) algorithm and Q-learning establish stronger theoretical foundations for their use in adaptive control and also in stability analysis of hybrid reinforcement learning and approximate reasoning-based controllers.
Berenji, Hamid R.↗
The Network Operations Control Center upgrade task: Lessons learned
This article synthesizes and describes the lessons learned from the Network Operations Control Center (NOCC) upgrade project, from the requirements phase through development and test and transfer. At the outset, the NOCC upgrade was being performed simultaneously with two other interfacing and dependent upgrades at the Signal Processing Center (SPC) and Ground Communications Facility (GCF), thereby adding a significant measure of complexity to the management and overall coordination of the development and transfer-to-operations (DTO) effort. Like other success stories, this project carried with it the traditional elements of top management support and exceptional dedication of cognizant personnel. Additionally, there were several NOCC-specific reasons for success, such as end-to-end system engineering, adoption of open-system architecture, thorough requirements management, and use of appropriate off-the-shelf technologies. On the other hand, there were several difficulties, such as ill-defined external interfaces, transition issues caused by new communications protocols, ambivalent use of two sets of policies and standards, and mistailoring of the new JPL management standard (due to the lack of practical guidelines). This article highlights the key lessons learned, as a means of constructive suggestions for the benefit of future projects.
Sherif, J. S.↗
RSRA/X-Wing flight control system development - Lessons learned
The X-Wing, in concept, marries the efficiencies of a helicopter and fixed wing aircraft through the use of a four-bladed wing/rotor that can be rotated or stopped in flight. The RSRA/X-Wing flight test program was a technology demonstration of this concept which, after three successful flights, was discontinued in late 1987. In spite of many technical challenges in this program, such as the use of circulation control, the fabrication of a large all-composite rotor, the development of an advanced, quadruplex digital flight control system, and the need for higher harmonic control, no major technical problems had been encountered at the time of the stop-work order. This paper addresses the issues of flight control system development and focuses on lessons learned. As with other such programs, software development was the most consuming issue. Other subjects of discussion include the problems of balancing program goals with technical goals, software- and hard-ware-related problems, safety issues, and system testing.
Corliss, Lloyd D.↗
Simultaneous Trajectory Tracking Control and Online Mass Estimation for a Regolith Excavating Robot via Integral Concurrent Learning
An adaptive controller is developed for a regolith excavation robot to determine the mass of excavated material and to account for the effects of gravity and friction while on the surface of other celestial bodies. A data-based integral concurrent learning (ICL) parameter update law accounts for and estimates the unknown mass, gravity, and friction parameters. A Lyapunov-based analysis proves that the trajectory tracking error and the parameter estimate errors exponentially converge to zero. An estimation of the mass of regolith excavated by the robot is calculated from the estimated parameters. A simulation study is performed to show the performance of the developed technique. Simulation results show that for 3 kilograms of excavated material, the mass estimate has an error of 4.9 grams.
Max L. Greene↗
Adaptive Control Systems, a General Classification Scheme Technical Note No. 2
Classification schema for finite-state adaptive control and learning systems
LEARNING SYSTEM↗
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↗
Real-Time Global Nonlinear Aerodynamic Modeling for Learn-To-Fly
Flight testing and modeling techniques were developed to accurately identify global nonlinear aerodynamic models for aircraft in real time. The techniques were developed and demonstrated during flight testing of a remotely-piloted subscale propeller-driven fixed-wing aircraft using flight test maneuvers designed to simulate a Learn-To-Fly scenario. Prediction testing was used to evaluate the quality of the global models identified in real time. The real-time global nonlinear aerodynamic modeling algorithm will be integrated and further tested with learning adaptive control and guidance for NASA Learn-To-Fly concept flight demonstrations.
Morelli, Eugene A.↗