Eccentricity and hardness control in cold rolling mills with a dynamically constructed neural controller

The main objective of a steel strip rolling process is to produce high quality steel at a desired thickness.  Thickness reduction is the result of the speed difference between the incoming and the outgoing steel strip and the application of the large normal forces via the backup and the work rolls.  Gauge control of a cold rolled steel strip is achieved using the gaugemeter principle that works adequately for the input gauge changes and the strip hardness changes.  However, the compensation of some factors is problematic, for example, eccentricity of the backup rolls.  This cyclic eccentricity effect causes a gauge deviation, but more importantly, a signal is passed to the gap position control so to increase the eccentricity deviation.  Consequently, the required high product tolerances are severely limited by the presence of the roll eccentricity effects.
In this paper a direct model reference adaptive control (MRAC) scheme with dynamically constructed neural controller was used.  The aim here is to find the simplest controller structure capable of achieving an optimal performance.  The stability of the adaptive neural control scheme (i.e. the requirement of persistency of excitation and bounded learning rates) is addressed by using as the inputs to the reference model the plant's state variables.  In such a case, excitation is due to actual plant signals (states) affected by plant disturbances and noise.  In addition, a reference model in the form of a filter with a desired transfer function using Modulus Optimum design was used to ensure variance in the desired dynamic characteristics of the system.  The gradually decreasing learning rate employed by the neural controller in this paper is aimed at eliminating controller instability resulting from over-aggressive control.  The moving target problem (i.e. the difficulty of global neural networks to perfrom several separate computational tasks in closed -loop control) is addressed by the localized architecture of the controller.  The above control scheme and learning algorithm offers a method for automatic discovery of an efficient controller.
The resulting neural controller produces an excellent disturbance rejection in both cases of eccentricity and hardness disturbances, reducing the gauge deviation due to eccentricity disturbance from 33.36% to 4.57% on average, and the gauge deviation due to hardness disturbance from 12.59% to 2.08%.

Excitability at the motoneuron pool and motor cortex is specifically modulated in lengthening compared to isometric contractions

Excitability at the motoneuron pool and motor cortex is specifically modulated in lengthening compared to isometric contractions. J Neurophysiol 101: 2030–2040, 2009. First published January 28, 2008; doi:10.1152/jn.91104.2008. Neural control of muscle contraction seems to be unique during muscle lengthening. The present study aimed to determine the specific sites of modulatory control for lengthening compared with isometric contractions. We used stimulation of the motor cortex and corticospinal tract to observe changes at the spinal and cortical levels. Motor-evoked potentials (MEPs) and cervicomedullary MEPs (CMEPs) were evoked in biceps brachii and brachioradialis during maximal and submaximal lengthening and isometric contractions at the same elbow angle. Sizes of CMEPs and MEPs were lower in lengthening contractions for both muscles (by 28 and 16%, respectively; P 0.01), but MEP-to-CMEP ratios increased (by 21%; P 0.05). These results indicate reduced excitability at the spinal level but enhanced motor cortical excitability for lengthening compared with isometric muscle contractions.

Altered responsiveness of the kidney to activation of the renal nerves in fat-fed rabbits

We tested whether mild adiposity alters responsiveness of the kidney to activation of the renal sympathetic nerves. After rabbits were fed a high-fat or control diet for 9 wk, responses to reflex activation of renal sympathetic nerve activity (RSNA) with hypoxia and electrical stimulation of the renal nerves (RNS) were examined under pentobarbital anesthesia. Fat pad mass and body weight were, respectively, 74% and 6% greater in fat-fed rabbits than controls. RNS produced frequency-dependent reductions in renal blood flow, cortical and medullary perfusion, glomerular filtration rate, urine flow, and sodium excretion and increased renal plasma renin activity (PRA) overflow. Responses of sodium excretion and medullary perfusion were significantly enhanced by fat feeding. For example, 1 Hz RNS reduced sodium excretion by 79 ± 4% in fat-fed rabbits and 46 ± 13% in controls. RNS (2 Hz) reduced medullary perfusion by 38 ± 11% in fat-fed rabbits and 9 ± 4% in controls. Hypoxia doubled RSNA, increased renal PRA overflow and medullary perfusion, and reduced urine flow and sodium excretion, without significantly altering mean arterial pressure (MAP) or cortical perfusion. These effects were indistinguishable in fat-fed and control rabbits. Neither MAP nor PRA were significantly greater in conscious fat-fed than control rabbits. These observations suggest that mild excess adiposity can augment the antinatriuretic response to renal nerve activation by RNS, possibly through altered neural control of medullary perfusion. Thus, sodium retention in obesity might be driven not only by increased RSNA, but also by increased responsiveness of the kidney to RSNA.

TMS stimulus-response asymmetry in left- and right handed individuals

There have been inconsistencies in the literature regarding asymmetrical neural control and results of experiments using TMS techniques. Therefore, the aim of this study was to further our understanding of the neural relationships that may underlie performance asymmetry with respect to the distal muscles of the hand using a TMS stimulus–response curve technique. Twenty-four male subjects (12 right handed, 12 left handed) participated in a TMS stimulus–response (S–R) curve trial. Focal TMS was applied over the motor cortex to find the optimal position for the first dorsal interossei muscle and to determine rest threshold (RTh). Seven TMS intensities ranging from 90 to 150 % of RTh were delivered in 10 % increments. One single TMS block consisted of 16 stimuli at each intensity. Peak-to-peak amplitudes were measured and the S–R curve generated. In right-handed subjects, the mean difference in slopes between the right and left hand was −0.011 ± 0.03, while the mean difference between hands in left-handed subjects was −0.049 ± 0.08. Left-handed normalized data in right handers displayed a mean of 1.616 ± 1.019 (two-tailed t test p < 0.05). The left-handed group showed a significant change in the normalized slope as indicated by a mean of 1.693 ± 0.149 (two-tailed t test p < 0.00006). The results found in this study reinforce previous work which suggests that there is an asymmetry in neural drive that exists in both left- and right-handed individuals. However, the results show that the non-dominant motor hemisphere displays a greater amount of excitability than the dominant, which goes against the conventional dogma. This asymmetry indicates that the non-dominant hemisphere may have a higher level of excitation or a lower level of inhibition for both groups of participants.

Cold rolling mill thickness control using the cascade-correlation neural network

The improvements in thickness accuracy of a steel strip produced by a tandem cold-roIling mill are of substantial interest to the steel industry. In this paper, we designed a direct model-reference adaptive control (MRAC)  scheme that exploits the natural level of excitation existing in the closed-loop with a dynamically constructed cascade-correlation neural network (CCNN) as a controller for cold roIling mill thickness control. Simulation results show that the combination of a such a direct MRAC scheme and the dynamically constructed CCNN significantly improves the thickness accuracy in the presence of disturbances and noise in comparison with to the conventional PID controllers.

Visual feedback control of a robot in an unknown environment (learning control using neural networks)

In this paper, a visual feedback control approach based on neural networks is presented for a robot with a camera installed on its end-effector to trace an object in an unknown environment. First, the one-to-one mapping relations between the image feature domain of the object to the joint angle domain of the robot are derived. Second, a method is proposed to generate a desired trajectory of the robot by measuring the image feature parameters of the object. Third, a multilayer neural network is used for off-line learning of the mapping relations so as to produce on-line the reference inputs for the robot. Fourth, a learning controller based on a multilayer neural network is designed for realizing the visual feedback control of the robot. Last, the effectiveness of the present approach is verified by tracing a curved line using a 6-degrees-of-freedom robot with a CCD camera installed on its end-effector. The present approach does not necessitate the tedious calibration of the CCD camera and the complicated coordinate transformations.

Fuzzy neural networks for control of dynamic systems

This thesis provides a unified and comprehensive treatment of the fuzzy neural networks as the intelligent controllers. This work has been motivated by a need to develop the solid control methodologies capable of coping with the complexity, the nonlinearity, the interactions, and the time variance of the processes under control. In addition, the dynamic behavior of such processes is strongly influenced by the disturbances and the noise, and such processes are characterized by a large degree of uncertainty. Therefore, it is important to integrate an intelligent component to increase the control system ability to extract the functional relationships from the process and to change such relationships to improve the control precision, that is, to display the learning and the reasoning abilities. The objective of this thesis was to develop a self-organizing learning controller for above processes by using a combination of the fuzzy logic and the neural networks. An on-line, direct fuzzy neural controller using the process input-output measurement data and the reference model with both structural and parameter tuning has been developed to fulfill the above objective. A number of practical issues were considered. This includes the dynamic construction of the controller in order to alleviate the bias/variance dilemma, the universal approximation property, and the requirements of the locality and the linearity in the parameters. Several important issues in the intelligent control were also considered such as the overall control scheme, the requirement of the persistency of excitation and the bounded learning rates of the controller for the overall closed loop stability. Other important issues considered in this thesis include the dependence of the generalization ability and the optimization methods on the data distribution, and the requirements for the on-line learning and the feedback structure of the controller. Fuzzy inference specific issues such as the influence of the choice of the defuzzification method, T-norm operator and the membership function on the overall performance of the controller were also discussed. In addition, the e-completeness requirement and the use of the fuzzy similarity measure were also investigated. Main emphasis of the thesis has been on the applications to the real-world problems such as the industrial process control. The applicability of the proposed method has been demonstrated through the empirical studies on several real-world control problems of industrial complexity. This includes the temperature and the number-average molecular weight control in the continuous stirred tank polymerization reactor, and the torsional vibration, the eccentricity, the hardness and the thickness control in the cold rolling mills. Compared to the traditional linear controllers and the dynamically constructed neural network, the proposed fuzzy neural controller shows the highest promise as an effective approach to such nonlinear multi-variable control problems with the strong influence of the disturbances and the noise on the dynamic process behavior. In addition, the applicability of the proposed method beyond the strictly control area has also been investigated, in particular to the data mining and the knowledge elicitation. When compared to the decision tree method and the pruned neural network method for the data mining, the proposed fuzzy neural network is able to achieve a comparable accuracy with a more compact set of rules. In addition, the performance of the proposed fuzzy neural network is much better for the classes with the low occurrences in the data set compared to the decision tree method. Thus, the proposed fuzzy neural network may be very useful in situations where the important information is contained in a small fraction of the available data.

Adaptive data based neural network leader-follower control of multi-agent networks

In this paper, we propose a data based neural network leader-follower control for multi-agent networks where each agent is described by a class of high-order uncertain nonlinear systems with input perturbation. The control laws are developed using multiple-surface sliding control technique. In particular, novel set of sliding variables are proposed to guarantee leader-follower consensus on the sliding surfaces. Novel switching is proposed to overcome the unavailability of instantaneous control output from the neighbor. By utilizing RBF neural network and Fourier series to approximate the unknown functions, leader-follower consensus can be reached, under the condition that the dynamic equations of all agents are unknown. An O(n) data based algorithm is developed, using only the network’s measurable input/output data to generate the distributed virtual control laws. Simulation results demonstrate the effectiveness of the approach.

Design of H∞ control of neural networks with time-varying delays

This paper deals with the H∞ control problem of neural networks with time-varying delays. The system under consideration is subject to time-varying delays and various activation functions. Based on constructing some suitable Lyapunov-Krasovskii functionals, we establish new sufficient conditions for H∞ control for two cases of time-varying delays: (1) the delays are differentiable and have an upper bound of the delay-derivatives and (2) the delays are bounded but not necessary to be differentiable. The derived conditions are formulated in terms of linear matrix inequalities, which allow simultaneous computation of two bounds that characterize the exponential stability rate of the solution. Numerical examples are given to illustrate the effectiveness of our results.

Observer-based control for time-varying delay neural networks with nonlinear observation

This paper studies the problem of designing observer-based controllers for a class of delayed neural networks with nonlinear observation. The system under consideration is subject to nonlinear observation and an interval time-varying delay. The nonlinear observation output is any nonlinear Lipschitzian function and the time-varying delay is not required to be differentiable nor its lower bound be zero. By constructing a set of appropriate Lyapunov-Krasovskii functionals and utilizing the Newton-Leibniz formula, some delay-dependent stabilizability conditions which are expressed in terms of Linear Matrix Inequalities (LMIs) are derived. The derived conditions allow simultaneous computation of two bounds that characterize the exponential stability rate of the closed-loop system. The unknown observer gain and the state feedback observer-based controller are directly obtained upon the feasibility of the derived LMIs stabilizability conditions. A simulation example is presented to verify the effectiveness of the proposed result.

Space vector modulation based fast speed response field-orientation control of induction motor drive with adaptive neural integrator

This paper presents a novel fast speed response control strategy for the poly-phase induction motor drive system based on flux angle. The control scheme is derived in rotor field coordinates and employs the estimation of the rotor flux and its position. An adaptive notch filter is proposed to eliminate the dc component of the integration of signals used for the rotor flux estimation. To improve the performance of the rotor flux estimator, derivative term of the back emf is incorporated in the system. The voltage components in the synchronous reference frame are generated in the controllers which are transformed to stationary reference frame for driving the motor. Space vector modulation technique is used here. Simulation of the drive system was carried out and the results were compared with those obtained for a system that produces the above mentioned voltage components using the conventional PI controller. It is observed that the proposed control methodology provides faster response than the conventional PI controller incorporated system.

Exponential stability for markovian jumping stochastic BAM neural networks with mode-dependent probabilistic time-varying delays and impulse control

Abstract
In this article, an exponential stability analysis of Markovian jumping stochastic bidirectional associative memory (BAM) neural networks with mode-dependent probabilistic time-varying delays and impulsive control is investigated. By establishment of a stochastic variable with Bernoulli distribution, the information of probabilistic time-varying delay is considered and transformed into one with deterministic time-varying delay and stochastic parameters. By fully taking the inherent characteristic of such kind of stochastic BAM neural networks into account, a novel Lyapunov-Krasovskii functional is constructed with as many as possible positive definite matrices which depends on the system mode and a triple-integral term is introduced for deriving the delay-dependent stability conditions. Furthermore, mode-dependent mean square exponential stability criteria are derived by constructing a new Lyapunov-Krasovskii functional with modes in the integral terms and using some stochastic analysis techniques. The criteria are formulated in terms of a set of linear matrix inequalities, which can be checked efficiently by use of some standard numerical packages. Finally, numerical examples and its simulations are given to demonstrate the usefulness and effectiveness of the proposed results.

Prediction interval-based control of nonlinear systems using neural networks

Prediction interval (PI) is a promising tool for quantifying uncertainties associated with point predictions. Despite its informativeness, the design and deployment of PI-based controller for complex systems is very rare. As a pioneering work, this paper proposes a framework for design and implementation of PI-based controller (PIC) for nonlinear systems. Neural network (NN)-based inverse model within internal model control structure is used to develop the PIC. Firstly, a PI-based model is developed to construct PIs for the system output. This model is then used as an online estimator for PIs. The PIs from this model are fed to the NN inverse model along with other traditional inputs to generate the control signal. The performance of the proposed PIC is examined for two case studies. This includes a nonlinear batch polymerization reactor and a numerical nonlinear plant. Simulation results demonstrated that the proposed PIC tracking performance is better than the traditional NN-based controller.