Search NASA⌕ Search

SEARCH · Search NASA

Results for “feedforward 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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

An intelligent control system for failure detection and controller reconfiguration

We present an architecture of an intelligent restructurable control system to automatically detect failure of system components, assess its impact on system performance and safety, and reconfigure the controller for performance recovery. Fault detection is based on neural network associative memories and pattern classifiers, and is implemented using a multilayer feedforward network. Details of the fault detection network along with simulation results on health monitoring of a dc motor have been presented. Conceptual developments for fault assessment using an expert system and controller reconfiguration using a neural network are outlined.

Biswas, Saroj K.↗
DOE OSTI2023

Data-Driven Model Predictive Control for Temperature Management of Heat Pipe Microreactor

To enable the self-regulating capability of heat pipe (HP) microreactors, an anticipatory control strategy through model predictive control (MPC) could proactively respond to potential disturbances and deviations in operating setpoints. However, a key factor prohibiting the widespread adoption of MPCs in nuclear applications is the effort and computational costs associated with learning and calibrating first-principles-based process models when the target system is complex and when there are gaps between modeled and target reactor systems. In this paper, we demonstrate data-driven MPC using three approaches for modeling the system dynamics, including a linear state-space model, feedforward neural network, and recurrent neural networks long short-term memory. We present the development and validation process of each model and compare the performance of data-driven MPCs in controlling the temperatures of selected HPs at the evaporator and condenser regions in a 37-HP-monolith system. Our results show that, qualitatively, all data-driven MPCs are producing similar control actions, while quantitatively, with artificial neural nets (especially feedforward neural nets), MPC can better follow drastic changes in setpoints with smallest errors.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS1991

Cascading a systolic array and a feedforward neural network for navigation and obstacle avoidance using potential fields

A technique is developed for vehicle navigation and control in the presence of obstacles. A potential function was devised that peaks at the surface of obstacles and has its minimum at the proper vehicle destination. This function is computed using a systolic array and is guaranteed not to have local minima. A feedfoward neural network is then used to control the steering of the vehicle using local potential field information. In this case, the vehicle is a trailer truck backing up. Previous work has demonstrated the capability of a neural network to control steering of such a trailer truck backing to a loading platform, but without obstacles. Now, the neural network was able to learn to navigate a trailer truck around obstacles while backing toward its destination. The network is trained in an obstacle free space to follow the negative gradient of the field, after which the network is able to control and navigate the truck to its target destination in a space of obstacles which may be stationary or movable.

Plumer, Edward S.↗
NASA NTRS2006

Instrument Pointing Control System for the Stellar Interferometry Mission - Planet Quest

This paper describes the high precision Instrument Pointing Control System (PCS) for the Stellar Interferometry Mission (SIM) - Planet Quest. The PCS system provides front-end pointing, compensation for spacecraft motion, and feedforward stabilization, which are needed for proper interference. Optical interferometric measurements require very precise pointing (0.03 as, 1-(sigma) radial) for maximizing the interference pattern visibility. This requirement is achieved by fine pointing control of articulating pointing mirrors with feedback from angle tracking cameras. The overall pointing system design concept is presentcd. Functional requirements and an acquisition concept are given. Guide and Science pointing control loops are discussed. Simulation analyses demonstrate the feasibility of the design.

control↗
NASA NTRS1987

A linear quadratic Gaussian with loop transfer recovery proximity operations autopilot for spacecraft

An automatic control scheme for spacecraft proximity operations is presented. The controller is capable of holding the vehicle at a prescribed location relative to a target, or maneuvering it to a different relative position using straight line-of-sight translations. The autopilot uses a feedforward loop to initiate and terminate maneuvers, and for operations at nonequilibrium set-points. A multivariate feedback loop facilitates precise position and velocity control in the presence of sensor noise. The feedback loop is formulated using the Linear Quadratic Gaussian (LQG) with Loop Transfer Recovery (LTR) design procedure. Linear models of spacecraft dynamics, adapted from Clohessey-Wiltshire Equations, are augmented and loop shaping techniques are applied to design a target feedback loop. The loop transfer recovery procedure is used to recover the frequency domain properties of the target feedback loop. The resulting compensator is integrated into an autopilot which is tested in a high fidelity Space Shuttle Simulator. The autopilot performance is evaluated for a variety of proximity operations tasks envisioned for future Shuttle flights.

Chen, George T.↗
NASA NTRS2001

Control of a simulated arm using a novel combination of Cerebellar learning mechanisms

We present a model of cerebellar cortex that combines two types of learning: feedforward predicitve association based on local Hebbian-type learning between granule cell ascending branch and parallel fiber inputs, and reinforcement learning with feedback error correction based on climbing fiber activity.

cerebellum cerebellar learning dynamic state estim↗
DOE OSTI2023

Neural network-based control of an ultrafast laser

With the recent advances in machine learning (ML) and data science (DS), the control, modeling, and analysis of these complex systems continues to improve. In this work, we report on the optimization of the intensity of a femtosecond laser using feedforward neural networks (FFNN) that model the input–output relationships of the data. The input parameters of the system were optimized to achieve the required performance of the femtosecond laser. We propose a neural network-based control system to model the relationship between the spectral amplitude and phase of the input laser pulse at the amplifier input and the shape of the output pulse. Low-jitter laser parameter inputs and the resulting laser pulse duration were modeled, and the resulting correlation between the input and output data was used to optimize the laser pulse. Here, we demonstrate improved processing and laser control performance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1997

Deadbeat Predictive Controllers

Several new computational algorithms are presented to compute the deadbeat predictive control law. The first algorithm makes use of a multi-step-ahead output prediction to compute the control law without explicitly calculating the controllability matrix. The system identification must be performed first and then the predictive control law is designed. The second algorithm uses the input and output data directly to compute the feedback law. It combines the system identification and the predictive control law into one formulation. The third algorithm uses an observable-canonical form realization to design the predictive controller. The relationship between all three algorithms is established through the use of the state-space representation. All algorithms are applicable to multi-input, multi-output systems with disturbance inputs. In addition to the feedback terms, feed forward terms may also be added for disturbance inputs if they are measurable. Although the feedforward terms do not influence the stability of the closed-loop feedback law, they enhance the performance of the controlled system.

Juang, Jer-Nan↗
DOE OSTI2025

Comprehensive assessment of deep reinforcement learning approaches for economic dispatch in nuclear-driven microgrids

As the electrical grid integrates more variable renewable energy sources such as wind and solar, the demand for distributed and flexible systems to address this increased variability becomes critical. Nuclear-driven microgrids provide a promising solution by offering stable generation to complement intermittent renewables, ensuring grid reliability and operating efficiency. This paper proposes a recurrent deep reinforcement learning framework for optimal economic dispatch in a nuclear-powered microgrid integrating renewable energy sources, small modular reactors, battery storage systems, and balance-of-plant dynamics. A three-agent control architecture is developed, where demand and renewable energy agents act as forecasters, and a reinforcement learning-based dispatch agent performs real-time energy allocation. A nonlinear programming formulation is first used to generate an optimal baseline for benchmarking. The proposed dispatch controller, based on Proximal Policy Optimization enhanced with Long Short-Term Memory networks, exploits temporal correlations in system dynamics by taking advantage of the time series used as inputs to improve policy robustness under uncertainty. Comparative analysis against established deep reinforcement learning methods, including Proximal Policy Optimization with a feedforward architecture, Soft Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient, demonstrates superior performance. Numerical results indicate that the proposed controller achieves a 0.39% cost reduction relative to the nonlinear programming benchmark and outperforms other learning-based methods by generating additional revenue of up to 0.35%. All reinforcement learning controllers compute dispatch actions in less than 0.3 s, resulting in a computational speedup of more than three orders of magnitude over the nonlinear programming baseline. The findings of this paper highlight their applicability for real-time operation and control in nuclear-integrated microgrids under volatile operating conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2007

Entry Attitude Controller for the Mars Science Laboratory

This paper describes the preliminary concept for the RCS 3-axis attitude controller for the exo-atmospheric and guided entry phases of the Mars Science Laboratory Entry, Descend and Landing. The entry controller is formulated as three independent channels in the control frame, which is nominally aligned with the stability frame. Each channel has a feedfoward and a feedback. The feedforward path enables fast response to large bank commands. The feedback path stabilizes the vehicle angle of attack and sideslip around its trim position, and tracks bank commands. The feedback path has a PD/D structure with deadbands that minimizes fuel usage. The performance of this design is demonstrated via simulation.

Mars↗
NASA NTRS1986

A model for the human's use of visual field cues in nap-of-the-Earth flight

A simple model is developed which describes the manner in which the human pilot may use visual field cues in controlling a vehicle in nap-of-the earth flight. The model is based upon the feedforward of information obtained from streamer patterns in the visual field to the inner-most loop of a multi-loop pilot/vehicle model. In this framework, the model is a logical extension of pursuit and preview models of the human operator which have appeared in the literature. Simulation and flight test data involving low-level helicopter flight tasks are applied to model development and validation.

Hess, R. A.↗
NASA NTRS1991

The application of neural networks to the SSME startup transient

Feedforward neural networks were used to model three parameters during the Space Shuttle Main Engine startup transient. The three parameters were the main combustion chamber pressure, a controlled parameter, the high pressure oxidizer turbine discharge temperature, a redlined parameter, and the high pressure fuel pump discharge pressure, a failure-indicating performance parameter. Network inputs consisted of time windows of data from engine measurements that correlated highly to the modeled parameter. A standard backpropagation algorithm was used to train the feedforward networks on two nominal firings. Each trained network was validated with four additional nominal firings. For all three parameters, the neural networks were able to accurately predict the data in the validation sets as well as the training set.

Meyer, Claudia M.↗
NASA NTRS1991

The application of neural networks to the SSME startup transient

Feedforward neural networks were used to model three parameters during the Space Shuttle Main Engine startup transient. The three parameters were the main combustion chamber pressure, a controlled parameter, the high pressure oxidizer turbine discharge temperature, a redlined parameter, and the high pressure fuel pump discharge pressure, a failure-indicating performance parameter. Network inputs consisted of time windows of data from engine measurements that correlated highly to the modeled parameter. A standard backpropagation algorithm was used to train the feedforward networks on two nominal firings. Each trained network was validated with four additional nominal firings. For all three parameters, the neural networks were able to accurately predict the data in the validation sets as well as the training set.

Meyer, Claudia M.↗
NASA NTRS1990

A real time neural net estimator of fatigue life

A neural net 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., turbopump 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. This neural net estimator of fatigue life is seen as the enabling technology to achieve component life prognosis, and therefore would be an important part of life extending control for reusable rocket engines.

Troudet, T.↗
DOE OSTI2026

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning

Spiking Neural Networks (SNNs) are computational models inspired by the event-driven communication and connectivity patterns of biological neural circuits. They enable high energy efficiency and natural support for diverse architectures ranging from layered networks to small-world and graphstructured topologies. In this work, we introduce NeuroCoreX, an open-source, FPGA-based spiking neural network emulator that provides real-time, on-chip learning and flexible network organization. NeuroCoreX supports both feedforward sensory inputs streamed directly from sensors or PCs via UART and recurrent on-chip connectivity, enabling simultaneous processing and learning from external stimuli and internal network dynamics-capabilities rarely available in existing FPGA SNN platforms. The system implements a Leaky Integrate-and-Fire (LIF) neuron model with current-based synapses and supports pair-based STDP learning on both feedforward and recurrent synapses. A lightweight Python interface enables interactive configuration, live monitoring, weight read-back, and experiment control. Importantly, NeuroCoreX is tightly integrated with the SuperNeuroMAT simulator, allowing SNN models to be transferred seamlessly from software to hardware for hardware-in-the-loop development. By combining real-time plasticity, flexible connectivity, and an open-source VHDL implementation, NeuroCoreX provides an extensible and accessible platform for neuromorphic research, algorithm-hardware co-design, and energy-efficient edge intelligence.

Gautam, Ashish [ORNL]↗
DOE OSTI2023

Machine Learning-Based Model Predictive Control of Two-Time-Scale Systems

In this study, we present a general form of nonlinear two-time-scale systems, where singular perturbation analysis is used to separate the dynamics of the slow and fast subsystems. Machine learning techniques are utilized to approximate the dynamics of both subsystems. Specifically, a recurrent neural network (RNN) and a feedforward neural network (FNN) are used to predict the slow and fast state vectors, respectively. Moreover, we investigate the generalization error bounds for these machine learning models approximating the dynamics of two-time-scale systems. Next, under the assumption that the fast states are asymptotically stable, our focus shifts toward designing a Lyapunov-based model predictive control (LMPC) scheme that exclusively employs the RNN to predict the dynamics of the slow states. Additionally, we derive sufficient conditions to guarantee the closed-loop stability of the system under the sample-and-hold implementation of the controller. A nonlinear chemical process example is used to demonstrate the theory. In particular, two RNN models are constructed: one to model the full two-time-scale system and the other to predict solely the slow state vector. Both models are integrated within the LMPC scheme, and we compare their closed-loop performance while assessing the computational time required to execute the LMPC optimization problem.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1998

Assessment Study of the State of the Art in Adaptive Control and its Applications to Aircraft Control

Many papers relevant to reconfigurable flight control have appeared over the past fifteen years. In general these have consisted of theoretical issues, simulation experiments, and in some cases, actual flight tests. Results indicate that reconfiguration of flight controls is certainly feasible for a wide class of failures. However many of the proposed procedures although quite attractive, need further analytical and experimental studies for meaningful validation. Many procedures assume the availability of failure detection and identification logic that will supply adequately fast, the dynamics corresponding to the failed aircraft. This in general implies that the failure detection and fault identification logic must have access to all possible anticipated faults and the corresponding dynamical equations of motion. Unless some sort of explicit on line parameter identification is included, the computational demands could possibly be too excessive. This suggests the need for some form of adaptive control, either by itself as the prime procedure for control reconfiguration or in conjunction with the failure detection logic. If explicit or indirect adaptive control is used, then it is important that the identified models be such that the corresponding computed controls deliver adequate performance to the actual aircraft. Unknown changes in trim should be modelled, and parameter identification needs to be adequately insensitive to noise and at the same time capable of tracking abrupt changes. If however, both failure detection and system parameter identification turn out to be too time consuming in an emergency situation, then the concepts of direct adaptive control should be considered. If direct model reference adaptive control is to be used (on a linear model) with stability assurances, then a positive real or passivity condition needs to be satisfied for all possible configurations. This condition is often satisfied with a feedforward compensator around the plant. This compensator must be robustly designed such that the compensated plant satisfies the required positive real conditions over all expected parameter values. Furthermore, with the feedforward only around the plant, a nonzero (but bounded error) will exist in steady state between the plant and model outputs. This error can be removed by placing the compensator also in the reference model. Design of such a compensator should not be too difficult a problem since for flight control it is generally possible to feedback all the system states.

Kaufman, Howard↗
NASA NTRS1990

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.↗