Estimating the parameters of the object of optimization
Statistical estimates for random search parameters in optimization of control system
Zuev, A. K.↗
SEARCH · Engineering Papers
Results for “random parameters”
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.
The effects of random errors in rawinsonde data on derived kinematic quantities
The sensitivity of kinematic parameters to random errors contained in rawinsonde data is assessed. Parameters under consideration include relative vorticity, vorticity advection, horizontal divergence, kinematic vertical motion, and temperature advection. It is shown that horizontal divergence is the most affected, with reliability a function of height. Vorticity advection is the next most altered by random error, and in this case, the effects of wind errors are greater on the gradient of vorticity than on the vorticity itself. Vertical motions are most affected by random perturbations at 300 mb and above, and temperature advection is found to be the least sensitive to random perturbations.
Belt, C. L.↗
Monitoring global geodynamical parameter variations with GPS and low earth satellites
A low earth satellite enhances global geodynamical parameters determination with GPS in two ways. First, it improves the GPS orbits, which in turn improve the estimates of other parameters. Secondly, a low earth satellite completes an orbit cycle in far shorter time (90 to 120 minutes) than do GPS satellites (12 hours); it observes more GPS satellites than a ground receiver does in shorter time and increases the correlation between GPS orbit errors. This reduces the error in the determination of nonrotational coordinate parameters, i.e., geocentric offset of ground tracking sites. Covariance results with the global geodynamical parameters modeled as constants, and as random-walk parameters to closer reflect the actual variations, are compared. The effects of using different GPS data quality and different ground tracking network are studied. The case of using two earth satellites in orthogonal orbital planes is also investigated.
Wu, S. C.↗
A new solution to parameter adaptive estimation of random processes
This paper is concerned with the development of an adaptive state estimator that is capable of tracking switched linear plants that undergo rapid configuration changes. The particular adaptive estimator developed here is called the Sliding Window Detector/Estimator (SWDE) algorithm. Unlike previous algorithms, the SWDE algorithm is designed specifically for the switched-linear plant problem. It uses a joint detection/estimation approach to give a very close approximation to the unrealizable optimum switched-linear estimator. An extremely reliable and accurate estimator can be constructed by combining a modified Parameter Adaptive Estimation (PAE) algorithm with SWDE. The algorithm has been fully verified by extensive computer simulation, and the implementation advantages afforded by this method make it suitable for use in a wide variety of applications.
Zwicke, P. E.↗
Probability Distribution Estimated From the Minimum, Maximum, and Most Likely Values: Applied to Turbine Inlet Temperature Uncertainty
Modern engineering design practices are tending more toward the treatment of design parameters as random variables as opposed to fixed, or deterministic, values. The probabilistic design approach attempts to account for the uncertainty in design parameters by representing them as a distribution of values rather than as a single value. The motivations for this effort include preventing excessive overdesign as well as assessing and assuring reliability, both of which are important for aerospace applications. However, the determination of the probability distribution is a fundamental problem in reliability analysis. A random variable is often defined by the parameters of the theoretical distribution function that gives the best fit to experimental data. In many cases the distribution must be assumed from very limited information or data. Often the types of information that are available or reasonably estimated are the minimum, maximum, and most likely values of the design parameter. For these situations the beta distribution model is very convenient because the parameters that define the distribution can be easily determined from these three pieces of information. Widely used in the field of operations research, the beta model is very flexible and is also useful for estimating the mean and standard deviation of a random variable given only the aforementioned three values. However, an assumption is required to determine the four parameters of the beta distribution from only these three pieces of information (some of the more common distributions, like the normal, lognormal, gamma, and Weibull distributions, have two or three parameters). The conventional method assumes that the standard deviation is a certain fraction of the range. The beta parameters are then determined by solving a set of equations simultaneously. A new method developed in-house at the NASA Glenn Research Center assumes a value for one of the beta shape parameters based on an analogy with the normal distribution (ref.1). This new approach allows for a very simple and direct algebraic solution without restricting the standard deviation. The beta parameters obtained by the new method are comparable to the conventional method (and identical when the distribution is symmetrical). However, the proposed method generally produces a less peaked distribution with a slightly larger standard deviation (up to 7 percent) than the conventional method in cases where the distribution is asymmetric or skewed. The beta distribution model has now been implemented into the Fast Probability Integration (FPI) module used in the NESSUS computer code for probabilistic analyses of structures (ref. 2).
Holland, Frederic A., Jr.↗
Multiobjective optimization in structural design with uncertain parameters and stochastic processes
The application of multiobjective optimization techniques to structural design problems involving uncertain parameters and random processes is studied. The design of a cantilever beam with a tip mass subjected to a stochastic base excitation is considered for illustration. Several of the problem parameters are assumed to be random variables and the structural mass, fatigue damage, and negative of natural frequency of vibration are considered for minimization. The solution of this three-criteria design problem is found by using global criterion, utility function, game theory, goal programming, goal attainment, bounded objective function, and lexicographic methods. It is observed that the game theory approach is superior in finding a better optimum solution, assuming the proper balance of the various objective functions. The procedures used in the present investigation are expected to be useful in the design of general dynamic systems involving uncertain parameters, stochastic process, and multiple objectives.
Rao, S. S.↗
A Bayesian approach to parameter and reliability estimation in the Poisson distribution.
For life testing procedures, a Bayesian analysis is developed with respect to a random intensity parameter in the Poisson distribution. Bayes estimators are derived for the Poisson parameter and the reliability function based on uniform and gamma prior distributions of that parameter. A Monte Carlo procedure is implemented to make possible an empirical mean-squared error comparison between Bayes and existing minimum variance unbiased, as well as maximum likelihood, estimators. As expected, the Bayes estimators have mean-squared errors that are appreciably smaller than those of the other two.
Canavos, G. C.↗
Parameter identification using a creeping-random-search algorithm
A creeping-random-search algorithm is applied to different types of problems in the field of parameter identification. The studies are intended to demonstrate that a random-search algorithm can be applied successfully to these various problems, which often cannot be handled by conventional deterministic methods, and, also, to introduce methods that speed convergence to an extremal of the problem under investigation. Six two-parameter identification problems with analytic solutions are solved, and two application problems are discussed in some detail. Results of the study show that a modified version of the basic creeping-random-search algorithm chosen does speed convergence in comparison with the unmodified version. The results also show that the algorithm can successfully solve problems that contain limits on state or control variables, inequality constraints (both independent and dependent, and linear and nonlinear), or stochastic models.
Parrish, R. V.↗
Derivation of phase statistics from the Mueller matrix
Experimental observations show a strong dependence of phase differences of scattering matrix elements on the physical parameters of random media. Here, the statistical behavior of the phase differences is studied for distributed targets. The pdfs of the phase differences are derived from the Mueller matrix of the target. In deriving the density functions, it is assumed that the real and imaginary parts of the copolarized and cross-polarized terms of the scattering matrix are jointly Gaussian and their covariance matrices are found in terms of the Mueller matrix elements. The functional forms of the copolarized and cross-polarized density functions are similar and are obtained independently. It is shown that the density function of the phase difference is completely determined in terms of only two parameters.
Sarabandi, K.↗
Sensitivity of an atmospheric photochemistry model to chlorine perturbations including consideration of uncertainty propagation
Models of stratospheric photochemistry are generally tested by comparing their predictions for the composition of the present atmosphere with measurements of species concentrations. These models are then used to make predictions of the atmospheric sensitivity to perturbations. Here the problem of the sensitivity of such a model to chlorine perturbations ranging from the present influx of chlorine-containing compounds to several times that influx is addressed. The effects of uncertainties in input parameters, including reaction rate coefficients, cross sections, solar fluxes, and boundary conditions, are evaluated using a Monte Carlo method in which the values of the input parameters are randomly selected. The results are probability distributions for present atmosheric concentrations and for calculated perturbations due to chlorine from fluorocarbons. For more than 300 Monte Carlo runs the calculated ozone perturbation for continued emission of fluorocarbons at today's rates had a mean value of -6.2 percent, with a 1-sigma width of 5.5 percent. Using the same runs but only allowing the cases in which the calculated present atmosphere values of NO, NO2, and ClO at 25 km altitude fell within the range of measurements yielded a mean ozone depletion of -3 percent, with a 1-sigma deviation of 2.2 percent. The model showed a nonlinear behavior as a function of added fluorocarbons. The mean of the Monte Carlo runs was less nonlinear than the model run using mean value of the input parameters.
Stolarski, R. S.↗
Adaptive stochastic control for a class of linear systems.
The problem considered in this paper deals with the control of linear discrete-time stochastic systems with unknown (possibly time-varying and random) gain parameters. The philosophy of control is based on the use of an open-loop feedback optimal (OLFO) control using a quadratic index of performance. It is shown that the OLFO system consists of (1) an identifier that estimates the system state variables and gain parameters and (2) a controller described by an 'adaptive' gain and correction term. Several qualitative properties and asymptotic properties of the OLFO adaptive system are discussed. Simulation results dealing with the control of stable and unstable third-order plants are presented. The key quantitative result is the precise variation of the control system adaptive gains as a function of the future expected uncertainty of the parameters; thus, in this problem the ordinary 'separation theorem' does not hold.
Tse, E.↗
Eigenvalue uncertainty in stressed structures.
A method is presented for calculating the statistics of the natural frequencies and mode shapes of vibration for a structure acted upon by an external static loading which results in the structure being stressed for eigenvalue analysis. The analytical tools presented apply to the probabilistic eigenvalue problem, and it is apparent that structural parameter uncertainty will significantly influence all aspects of the structure's response. The treatment of a sample problem serves the purpose of furthering understanding for the importance of considering structural parameters as random variables.
Hart, G. C.↗
Acoustic and vibration environments for laboratory experiments in space
The basic parameters of random noise and vibration are described, and typical environments for the launch phase and orbital operations are presented. For the latter, both acoustically induced and structure-borne, thruster-included vibration are addressed, using data obtained during the Skylab and Titan programs.
Rader, W. P.↗
Procedure for generating ground wind environments for Shuttle liftoff studies
Ground-wind environments for Monte Carlo simulations of Space Shuttle liftoff at KSC are developed. Input parameters include randomly selected 18.3-m-altitude peak wind speed (from which mean wind profile and turbulence intensity are calculated), randomly selected mean wind direction, and longitudinal and lateral turbulence components obtained from the Shuttle-simulation turbulence tapes (SSTT: Tatom et al., 1982). The steps in the simulation of turbulence time histories and horizontal wind fields are listed. It is found that separate statistical analysis of each hour-season pair, applying data on the time fraction of occurrence of peak winds and wind directions at KSC, will be necessary to interpret simulation results consistently.
Fichtl, G. H.↗
Simplified Worst-Case Analysis of Complex Systems
Statistical method avoids excessive computer time. Technique involves simplified Monte Carlo simulation of system with randomly chosen parameters and comparison of tolerance extremes of several of worst-case situations found. Resulting combination of tolerance extremes then used in detailed analysis - one that makes use of full complex nonlinear model capable of accurate simulations.
Pond, C. L.↗
SARSAT 406 MHz system technical evaluation
The location accuracy, access to spacecraft, uplink margin, and interference problems of the COSPAS-SARSAT system are reviewed. Over 90% of positions are accurate to within 5 km, in local mode, slightly worse in global mode. The random access parameters of SARSAT provide for the location of up to 90 beacons with a uniform distribution in the satellite visibility circle (2600 km radius). The ratio of messages correctly processed on board to messages transmitted to the satellite is 0.8, increasing as number of beacons decreases. Interference, particularly over western Europe and the United States degrades performance, but sources can be located.
Goudy, P.↗
Discrete-time Markovian-jump linear quadratic optimal control
This paper is concerned with the optimal control of discrete-time linear systems that possess randomly jumping parameters described by finite-state Markov processes. For problems having quadratic costs and perfect observations, the optimal control laws and expected costs-to-go can be precomputed from a set of coupled Riccati-like matrix difference equations. Necessary and sufficient conditions are derived for the existence of optimal constant control laws which stabilize the controlled system as the time horizon becomes infinite, with finite optimal expected cost.
Chizeck, H. J.↗
Random loading fatigue crack growth: Crack closure considerations
The prediction of fatigue crack growth is an important element of effective fracture control for metallic structures and mechanical components, especially in the aerospace industry. The prediction techniques available and applied today are mostly based on fatigue crack growth measurements determined in constant amplitude testing. However, while many service loadings are constant amplitude, many more loadings are random amplitude. An investigation to determine which statistics of random loadings are relevant to fatigue crack closure was conducted. The fundamentals of random processes and crack closure are briefly reviewed, then the relevance of certain random process parameters to the crack closure calculation are discussed qualitatively. A course for further research is outlined.
Ortiz, Keith↗