Gene/Protein Disease Symptom Drug Enzyme Compound
Pivot Concepts:   Target Concepts:
Query: UMLS:C0598853 (forgetting)
 3,232 document(s) hit in 31,850,051 MEDLINE articles (0.00 seconds)

An innovative neurofuzzy network is proposed herein for pattern classification applications, specifically for vibration monitoring. A fuzzy set interpretation is incorporated into the network design to handle imprecise information. A neural network architecture is used to automatically deduce fuzzy if-then rules based on a hybrid supervised learning scheme. The neurofuzzy classifier proposed is equipped with a one-pass, on-line, and incremental learning algorithm. This network can be considered a self-organized classifier with the ability to adaptively learn new information without forgetting old knowledge. The classification performance of the proposed neurofuzzy network is validated on the Fisher's Iris data, which is a well-known benchmark data set. For the generalization capability, the neurofuzzy network can achieve 97.33% correct classification. In addition, to demonstrate the efficiency and effectiveness of the proposed neurofuzzy paradigm, numerical simulations have been performed using the Westland data set. The Westland data set consists of vibration data collected from a US Navy CH-46E helicopter test stand. Using a simple fast Fourier transform technique for feature extraction, the proposed neurofuzzy network has shown promising results. Using various torque levels for training and testing, the network achieved 100% correct classification.
ISA Trans 2000
PMID:Pattern classification by a neurofuzzy network: application to vibration monitoring. 1100 61

In this paper five multivariable adaptive and classical control strategies have been studied and implemented in a simulator of the copper grinding plant of CODELCO-Andina. The strategies presented were compared and, according to theory, exhibit good behavior. The extended horizon, pole-placement and model reference multivariable adaptive control strategies were formulated in discrete-time and use a model of the plant whose parameters are updated on line using the recursive least squares method along with UD factorization of the covariance matrix and variable forgetting factor. The direct Nyquist array and sequential loop closing techniques were also studied and simulated. The two-by-two multivariable system chosen to represent the grinding plant has the percentage of solids (density) of the pulp fed to the hydrocyclones (which is highly correlated with the percentage of +65 mesh in the overflow of hydrocyclones) and the sump level as output (controlled) variables. The water flow added to the sump and the speed of the pump are its input (manipulated) variables. All the algorithms tested by simulation exhibited good performance and were able to control the grinding plant in a stable fashion. Adaptive algorithms showed better performance than classical techniques, with the extended horizon and pole-placement algorithms proving to be the best. The fact that adaptive algorithms continuously adjust their parameters renders such controllers superior to those based on fixed parameters.
ISA Trans 2002 Jan
PMID:Multivariable control of grinding plants: a comparative simulation study. 1201 4

The purpose of this study was to examine improvements to reinforcement learning (RL) algorithms in order to successfully interact within dynamic environments. The scope of the research was that of RL algorithms as applied to robotic navigation. Proposed improvements include: addition of a forgetting mechanism, use of feature based state inputs, and hierarchical structuring of an RL agent. Simulations were performed to evaluate the individual merits and flaws of each proposal, to compare proposed methods to prior established methods, and to compare proposed methods to theoretically optimal solutions. Incorporation of a forgetting mechanism did considerably improve the learning times of RL agents in a dynamic environment. However, direct implementation of a feature-based RL agent did not result in any performance enhancements, as pure feature-based navigation results in a lack of positional awareness, and the inability of the agent to determine the location of the goal state. Inclusion of a hierarchical structure in an RL agent resulted in significantly improved performance, specifically when one layer of the hierarchy included a feature-based agent for obstacle avoidance, and a standard RL agent for global navigation. In summary, the inclusion of a forgetting mechanism, and the use of a hierarchically structured RL agent offer substantially increased performance when compared to traditional RL agents navigating in a dynamic environment.
ISA Trans 2004 Apr
PMID:Reinforcement learning algorithms for robotic navigation in dynamic environments. 1509 82

Considering the performances of conventional Kalman filter may seriously degrade when it suffers stochastic faults and unknown input, which is very common in engineering problems, a new type of adaptive three-stage extended Kalman filter (AThSEKF) is proposed to solve state and fault estimation in nonlinear discrete-time system under these conditions. The three-stage UV transformation and adaptive forgetting factor are introduced for derivation, and by comparing with the adaptive augmented state extended Kalman filter, it is proven to be uniformly asymptotically stable. Furthermore, the adaptive three-stage extended Kalman filter is applied to a two-dimensional radar tracking scenario to illustrate the effect, and the performance is compared with that of conventional three stage extended Kalman filter (ThSEKF) and the adaptive two-stage extended Kalman filter (ATEKF). The results show that the adaptive three-stage extended Kalman filter is more effective than these two filters when facing the nonlinear discrete-time systems with information of unknown inputs not perfectly known.
ISA Trans 2018 Apr
PMID:An adaptive three-stage extended Kalman filter for nonlinear discrete-time system in presence of unknown inputs. 2947 68

Electro-hydraulic shake table (EHST), also known as earthquake simulator, is of considerable significance in civil engineering for evaluating structures or infrastructures subjected to earthquake ground motions. However, reproduction of prescribed accelerations at table for EHST systems remains to be imperfect as the whole systems are confronted with hydraulic nonlinearity, varying dynamics, unexpected disturbance, etc. For enhancing the acceleration tracking performance of EHST systems, an acceleration waveform reproduction strategy using offline designed parametric feedforward compensator (PFC) and online functional link adaptive controller (FLAC) is proposed in this paper. The PFC controller is established on the basis of classical three variable controller (TVC) as an inner compensation loop, in which multi-innovation forgetting gradient (MIFG) algorithm together with zero magnitude error tracking (ZMET) technique are utilized during the design process. The FLAC controller is combined to the PFC controller as an outer loop for further acceleration enhancement purpose, and the controller's nonlinear mapping ability is achieved with trigonometric expansion implementation. Following theoretical analysis of the proposed controller, comparative experiments are performed on an established unidirectional EHST test bench with both random and real-time recorded earthquake input waveforms. The experimental results validate the feasibility and superiority of the proposed acceleration reproduction strategy.
ISA Trans 2018 Dec
PMID:Investigation on acceleration performance improvement of electro-hydraulic shake tables using parametric feedforward compensator and functional link adaptive controller. 3019 22

In this paper, to improve the positioning accuracy of LED chip, a dual rate adaptive fading Kalman filter algorithm with delay compensation is proposed and applied to the LED chip visual servo positioning system. Firstly, a structure of dual rate Kalman filter is introduced to the visual servo control system, which compensate the visual information delay and realize the accurate time sequential coordination of encoder and visual feedback. Then, considering the inaccuracy of system mathematical model, the adaptive forgetting factor is added to the iterative process of above algorithm, and the impact of accumulated model error on system stability is consequently mitigated. Finally, the experimental results show that the proposed method obviously decreases the positioning errors of LED chip and is robust to inaccuracy and uncertainty of system model parameters.
ISA Trans 2019 Apr
PMID:LED chip accurate positioning control based on visual servo using dual rate adaptive fading Kalman filter. 3052 16