Search

An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) approach to the adaptive inverse control (AIC) problem is shown to outperform the adaptive filtering techniques and algorithms normally used in adaptive control, especially when in nonlinear plants. The deeper the controller, the better the inverse function approximation, provided that the nonlinear plant has an inverse and that this inverse can be approximated. Simulation results prove the feasibility of this DL-based adaptive inverse control scheme. The DL-based AIC system is robust to nonlinear plant parameter changes in that the plant output reassumes the value of the reference signal considerably faster than with the adaptive filter counterpart of the deep neural network. The settling and rise times of the step response are shown to improve in the DL-based AIC system. [ABSTRACT FROM AUTHOR]

Copyright of China Mechanical Engineering is the property of Editorial Board of China Mechanical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper presents a new scheme for the control of unknown block-oriented nonlinear systems using spline adaptive filter (SAF). The principle of adaptive inverse control (AIC) is utilized as the control structure in this scheme. First, the mathematical model of the unknown controlled plant was established through SAF, which consists of a linear FIR filter and a nonlinear spline interpolation function. The controller is obtained by adaptively establishing the inverse model of linear FIR filter and nonlinear spline function, respectively. In this process, a shift form DCT-LMS with variable learning rate (VL-DCTS-LMS) algorithm is proposed in order to adapt the inverse of FIR filter, and a modified Newton–Raphson method is used for directly calculating the inverse of spline interpolation function. Considering the steady-state error resulted by the plant modeling inaccuracy, filtered error feedback is introduced into the plant input in order to eliminate the control error. The effectiveness of the proposed control scheme is verified by several numerical examples, including some additional discussions and a comparison with other control methods. [ABSTRACT FROM AUTHOR]

This article involves the adaptive inverse control of a coupled vessel-riser system with input backlash and system uncertainties. By introducing an adaptive inverse dynamics of backlash, the backlash control input is divided into a mismatch error and an expected control command, and then a novel adaptive inverse control strategy is established to eliminate vibration, tackle backlash, and compensate for system uncertainties. The bounded stability of the controlled system is analyzed and demonstrated by exploiting the Lyapunov’s criterion. The simulation comparison experiments are finally presented to verify the feasibility and effectiveness of the control algorithm. [ABSTRACT FROM AUTHOR]

This paper address an adaptive stabilizing controller for inverted pendulum on a cart based on feedback linearization coupled with an adaptive fuzzy logic based swing up controller. First feedback linearizing control signal is derived by decomposing the system into cart subsystem and pendulum subsystem. Then adaptive inverse control technique will be applied to each feedback linearizing control signals. An adaptive inverse control method is used for compensation of unknown parameters of an inverted pendulum on a cart, while feedback linearization is used to cancel non-linearity in the system. The pendulum will be driven from it's pendant position to inverted position using an adaptive fuzzy logic based swing up controller. When the pendulum reaches near it's inverted position, the stabilizing controller takes over the swing up controller. The MATLAB/SIMULINK simulation shows that the proposed controllers adapt to unknown mass of a cart between 0:1kg - 4kg and mass of a pendulum between 0:01kg - 4kg. [ABSTRACT FROM AUTHOR]

In this paper, a new adaptive inverse control (AIC) method is presented to solve vehicle handling inverse dynamics problem and achieve path tracking control for emergency avoidance. The designed AIC system includes two crucial modules: the model identifier and the inverse model controller which are both the nonlinear adaptive filters constituted by neural networks. Firstly, they are both trained offline and connected with the vehicle to be the initial states of AIC system. Then, the back-propagation (BP) algorithm is used to adjust the weight parameters of the model identifier to identify the nonlinear characteristics of vehicle in real time. Simultaneously, the inverse model controller is used to be the controller of AIC system and the controller's weight parameters are tuned by the back-propagation through model (BPTM) algorithm online. A novel adaptive learning rate is introduced into the BP algorithm and the BPTM algorithm to guarantee the stability of neural networks. Finally, the inverse model controller can be regarded as the inverse of vehicle and used to solve required steering wheel angle according to the desired path to realize path tracking. The double lane change (DLC) road is used to be the desired path for emergency avoidance. The simulation results illustrate that the AIC system could realize accurate path tracking although there exist external disturbances and the AIC is an effective method to deal with the handling inverse dynamics problem for emergence avoidance. [ABSTRACT FROM AUTHOR]

An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) approach to the adaptive inverse control (AIC) problem is shown to outperform the adaptive filtering techniques and algorithms normally used in adaptive control, especially when in nonlinear plants. The deeper the controller, the better the inverse function approximation, provided that the nonlinear plant has an inverse and that this inverse can be approximated. Simulation results prove the feasibility of this DL-based adaptive inverse control scheme. The DL-based AIC system is robust to nonlinear plant parameter changes in that the plant output reassumes the value of the reference signal considerably faster than with the adaptive filter counterpart of the deep neural network. The settling and rise times of the step response are shown to improve in the DL-based AIC system.

We present a method for control in real-time hybrid simulation (RTHS) that relies exclusively on data processing. Our approach bypasses conventional control techniques, which presume availability of a mathematical model for the description of the control plant (e.g., the transfer system and the experimental substructure) and applies a simple plug 'n play framework for tuning of an adaptive inverse controller for use in a feedforward manner, avoiding thus any feedback loops. Our methodology involves (i) a forward adaptation part, in which a noise-free estimate of the control plant's dynamics is derived; (ii) an inverse adaptation part that performs estimation of the inverse controller; and (iii) the integration of a standard polynomial extrapolation algorithm for the compensation of the delay. One particular advantage of the method is that it requires tuning of a limited set of hyper-parameters (essentially three) for proper adaptation. The efficacy of our framework is assessed via implementation on a virtual RTHS (vRTHS) benchmark problem that was recently made available to the community. The attained results indicate that data-driven RTHS may form a competitive alternative to conventional control.

Focusing on the nonlinear time-delay systems actuated by smart-material-based actuators, an adaptive dynamic surface estimated inverse motion control scheme is proposed in this article. The asymmetric hysteresis nonlinearity is counteracted by constructing its evaluated inverse compensator. A state estimator is constructed to estimate the unmeasurable states and at the same time to cope with external disturbances. The assumptions on time-delay functions are removed, and the unknown time-delay function is online evaluated by combining the fuzzy logic system with a finite covering lemma. Also, the prespecified tracking performance is achieved by utilizing an error-transformed function. Experimental results of the proposed controller are performed on the piezoelectric positioning stage to verify the effectiveness of the control scheme. [ABSTRACT FROM AUTHOR]

In this paper, a new active vibration control system has been proposed for the elimination of boring bar chatter in the internal turning process. The system is composed of a boring bar equipped with electromagnetic actuator and accelerometer, as well as a novel adaptive control algorithm that is widely used in the field of active noise control. The controller is known as feedback FxNLMS and is composed of two finite impulse response adaptive filters. One of the filters is known as a model filter, which predicts the dynamic model of actuator-boring bar assembly. The other is known as the control filter and anticipates the inverse model of forwarding path dynamics. The weight vector of the adaptive filter is adjusted by using the normalized least mean square algorithm. Firstly, the impact test is conducted in the presence of an adaptive controller. It is observed that the magnitude of the dominant mode on the forward path’s frequency response function is drastically suppressed by 36 dBs. Secondly, the internal turning tests are conducted on Aluminum alloy 6063-T6, to investigate the performance of the adaptive controller for the purpose of chatter mitigation. Due to the optimal performance of the adaptive controller, the dominant magnitude of the boring bar’s power spectral density is successfully attenuated up to 68 dBs, and the critical limiting depth of cut is increased by 10 folds. Also, the roughness of the machined surface is remarkably improved by 8 folds compared to the control-off cutting test. Moreover, the actuator cost is considerably reduced by 3 folds in comparison to the optimal constant-gain integral controller. [ABSTRACT FROM AUTHOR]

• Electrohydraulic shaking table (EHST) system includes servo and target controller. • The effective frequency bandwidth is extended by new designed servo controller. • An adaptive power level control algorithm is proposed for target control. • Experiment was conducted on a 3-ton EHST system with a 1.2 m × 1.2 m table. • The results show the system can finally match the target within an accuracy of ±3 dB. Active vibration control using electrohydraulic shaking table (EHST) system is widely applied in civil engineering, automotive industry, environmental vibration testing and other situations where large actuating forces are needed. However, the electrohydraulic actuators (actuating systems) often suffer from drawbacks of limited frequency bandwidth, varying system parameters and so forth. In view of the limits mentioned above, this study hopes to seek out proper solutions to minimize the influence from those drawbacks. We first design a full state feedback-feedforward servo controller, which is able to extend the frequency bandwidth of EHST system, by constructing the analytical models of the servo valve and hydraulic cylinder. Numerical simulations show that the proposed servo controller is able to compensate for the attenuation-band of hydraulic cylinder and thus improve the upper frequency limit of the whole system to a degree that is higher than the natural frequency of servo valve. Afterwards, we propose a frequency domain adaptive power level control (APLC) algorithm for solving the problem of parametric variations of EHST system in application of power level control (i.e., simulate vibration based on certain power spectrum). Numerical simulations show that although APLC algorithm is not able to get exactly same spectrum and waveform at every independent trial, the power level of every trail will finally converge to the target power spectrum. Finally, an experimental validation was conducted based on an EHST system with 3 ton maximum force and 1.2 m × 1.2 m horizontal table. The results show that the proposed algorithms have greatly improved the effective bandwidth and the power level of the controlled system response can finally match the target power spectrum within an accuracy of ±3 dB. [ABSTRACT FROM AUTHOR]

Taking the hot-rolling products made by an iron and steel company as the research object, this paper builds the inverse model reflecting the relationship between the hot-rolling steel product performance indicators, the chemical composition of steel and the rolling technological parameters by using the BP neural network. So the purpose of getting technological parameters is achieved, according to the given steel performance indicators. Combining the BP neural network, adaptive inverse control with internal model control theory, this paper builds the BP neural network inverse model with multiple input and single output based on internal model control. Therefore, it realizes the inverse mapping between the output and the input variables of the BP neural network. And the output variables can be obtained according to the input variables. Besides, this paper also gives the detailed steps to solve the inverse model. Then, the model is applied to the hot-rolling steel products quality control system. The performance indicators of the hot-rolling products are set up, and the rolling technological parameters—the rolling crimp temperature—are solved. The model realizes the controllability of rolling technological parameters. Finally, through the verification of hot-rolling products quality control positive system, the error is in line with the enterprise production requirements. [ABSTRACT FROM AUTHOR]

In this paper, adaptive inverse position control is applied to switched reluctance motor (SRM) with simplified interval type-2 fuzzy neural networks (SIT2FNNs). The proposed adaptive inverse position control scheme for the SRM can be divided into the design of two control loops. The first loop is used for the position control, which is designed based on the adaptive inverse control (AIC). And the AIC is constructed with two SIT2FNNs, which are applied to identification and control for the SRM, respectively. The second loop is used for the current control, which is realized with the current-sharing method (CSM). Simulation results certify the effectiveness of the proposed control scheme in the achievement on high position control precision and perfect dynamic performance for the SRM. [ABSTRACT FROM AUTHOR]

The gripper rotation system of a heavy-duty manipulator is generally driven by hydraulic motors, and it is difficult to guarantee the accuracy of the rotation angle using conventional control methods due to the existence of dead zones with unknown characteristics. This paper proposes an adaptive inverse dead-zone control method, in which the gradient projection technique is applied to design an adaptive updating law for estimating the inverse dead-zone parameters online. First, a dynamic model of the gripper rotation system is presented with an analysis of its dead-zone characteristics. Then, the controller is designed based on a Takagi–Sugeno fuzzy model, and the estimated values of the inverse dead-zone parameters are shown to converge to their true values. Finally, the performance of the proposed adaptive control method is experimentally demonstrated on an actual forging manipulator. Comparisons with a fixed inverse dead-zone control method demonstrate the effectiveness and applicability of the proposed control method. [ABSTRACT FROM PUBLISHER]

Compared with conventional piezoelectric inchworm actuators (PIAs), which rely on a frictional mechanism to produce large stroke and force outputs, PIAs equipped with MEMS ridges can achieve much higher power density in small geometries through the interlocking of micro-ridges. This is promising for future adaptive space structure applications. However, from a practical perspective, achieving stable interlocking MEMS ridges remains challenging, and so an accurate structural assembly and effective control strategy are required. This paper presents an actuator with a simple structure, thus simplifying the assembly process and reducing assembly errors, and then designs a reasonable control strategy that compensates for hysteresis and the uncertain compression of the structure induced by acting against external loads of different stiffness. Finally, the stable interlocking of MEMS ridges is experimentally validated by measuring the significant improvement in PIA load capacity. [ABSTRACT FROM AUTHOR]

Type-2 Fuzzy Neural Networks have tremendous capability in identification and control of nonlinear, time-varying and uncertain systems. In this paper the procedure of designing inverse adaptive type-2 fuzzy neural controller for online control of nonlinear dynamical systems will be presented. At first the structure of a novel class of Interval Type-2 Nonlinear Takagi-Sugeno-Keng Fuzzy Neural Networks (IT2-NTSK-FNN) will be presented. There is a class of nonlinear function of inputs in the consequent part of fuzzy rules. This IT2-NTSK-FNN comprises seven layers and the fuzzification is done in two first layers including type-2 fuzzy neurons with uncertainties in the mean of Gaussian membership functions. Third layer is rule layer and model reduction occurs in fourth layer via adaptive nodes. Fifth, sixth and seventh layers are consequent layer, centroid rules' calculation layer and output layer respectively. For training the network back propagation (steepest descend) method with adaptive training rate is used. Finally, three methods including online adaptive inverse controller based on IT2-NTSK-FNN, IT2-TSK-FNN (linear consequent part) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are employed to control of a magnetic ball levitation system. External disturbances and uncertainty in parameters are considered in the model of magnetic ball levitation system. Simulation results show the efficacy of the proposed method. [ABSTRACT FROM AUTHOR]

This paper is concerned with the problem of type-2 fuzzy adaptive inverse control for a cable-driven parallel system. Based on the heuristics and prior knowledge of the system, the system is divided into six subsystems. The proposed control scheme for each subsystem contains a forward model and a fuzzy adaptive inverse controller (FAIC), which are expressed by an interval type-2 fuzzy nonlinear autoregressive exogenous (NARX) model, respectively. To construct the antecedents of the interval type-2 fuzzy NARX forward models and FAICs, the monotonic property of the fuzzy NARX model is first proved, and then, their antecedent parameters can be determined by this property. Furthermore, the consequent parameters of the forward models are computed offline via a constrained least squares algorithm, and the consequent parameters of the FAIC are adjusted online via a recursive least squares algorithm. Experiment results are provided to show that the proposed type-2 fuzzy control scheme can realize the control objectives and achieve a good control performance. [ABSTRACT FROM PUBLISHER]

Accurate reproduction of time series with diverse frequency characteristics is a central issue in structural testing. This is true not only for simple experimental tests performed by reaction walls or shaking tables but also for more sophisticated ones, such as hybrid testing. Especially in the latter case, where actual feedback from an ongoing test is used in the calculation of the next excitation value, any possible mismatch may be fatal for both the validity of the test and the safety. The objective of this study is to propose a framework for the adaptive inverse control of shaking tables, which succeeds in this matching to a certain degree. By formulating a critical set of design specifications that correspond to safety, implementation, robustness and ease of use, the conducted research results in a design that is based on a modified version of the filtered-X algorithm with very competitive features. These are the following: (i) default operation in hard real-time and acceleration mode; (ii) very low hardware requirements; (iii) effective cancelation of the shaking table's dynamics; and (iv) robustness against specimen dynamics. For its practical evaluation, the method is applied to shaking table waveform replication tests under the installation of an approximately linear specimen of sufficiently high mass and complex geometry. The results are promising and suggest further research toward this field, especially in conjunction with hybrid testing, as the method retains certain global applicability attributes and it can be easily extended to other transfer systems, apart from shaking tables. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Different microsources have different frequency regulation functions and capabilities. The droop control can allocate power among the microsources according to the operation demand during system dynamics; however, the steady-state frequency often deviates from the rated value because of the droop characteristics. To ensure the precise condition of power and the stability of frequency even in a low-voltage network, this paper puts forward an improved droop control algorithm based on coordinate rotational transformation. With the ability to accurately regulate the unbalance power, this method realizes self-discipline parallel operation of microsources. Furthermore, an adaptive inverse control strategy applied to modified power conditioning is developed. With an online adjustment of modified P-f droop coefficient for the frequency of microgrid to track the rated frequency, the strategy guarantees maintaining the frequency of microgrid at the rated value and meeting the important customers' frequency requirements. The simulation results from a multibus microgrid show the validity and feasibility of the proposed control scheme. [ABSTRACT FROM AUTHOR]

We propose an adaptive inverse control scheme, which employs a neural network for the system identification phase and updates its weights in online mode. The theoretical basis of the method is given and its performance is illustrated by means of its application to different control problems showing that our proposal is able to overcome the problems generated by dynamic nature of the process or by physical changes of the system which originate important modifications in the process. A comparative experimental study is presented in order to show the more stable behavior of the proposed method in several working ranks. [ABSTRACT FROM AUTHOR]

Abstract: This article presents a high fidelity acceleration time waveform replication (TWR) on an electro-hydraulic shaking table (EHST) using the hybrid control combined with an offline feed-forward compensator and an online adaptive inverse control (AIC). This study applies the acceleration and velocity feedback to improve the steady performance of the EHST, and employs the system inverse transfer function (ITF) of the acceleration closed-loop system to extend the frequency bandwidth and a modeling error compensator to improve the dynamic characteristics. Moreover, the investigation utilizes a Zero Phase Error Tracking Controller to improve the accuracy of the designed ITF. The proposed hybrid controller also utilizes an online AIC for a high fidelity TWR after that the dynamic characteristics has been improved by the feedback and feed-forward controllers. Thus, the proposed hybrid control strategy combines the merits of the offline feed-forward compensation and online AIC. Performance analysis and comparison of the experimental results demonstrate that better replication accuracy with the proposed hybrid control can be achieved in experiments on an actual EHST. [Copyright &y& Elsevier]

The precise control of spiking in a population of neurons via applied electrical stimulation is a challenge due to the sparseness of spiking responses and neural system plasticity. We pose neural stimulation as a system control problem where the system input is a multidimensional time-varying signal representing the stimulation, and the output is a set of spike trains; the goal is to drive the output such that the elicited population spiking activity is as close as possible to some desired activity, where closeness is defined by a cost function. If the neural system can be described by a time-invariant (homogeneous) model, then offline procedures can be used to derive the control procedure; however, for arbitrary neural systems this is not tractable. Furthermore, standard control methodologies are not suited to directly operate on spike trains that represent both the target and elicited system response. In this paper, we propose a multiple-input multiple-output (MIMO) adaptive inverse control scheme that operates on spike trains in a reproducing kernel Hilbert space (RKHS). The control scheme uses an inverse controller to approximate the inverse of the neural circuit. The proposed control system takes advantage of the precise timing of the neural events by using a Schoenberg kernel defined directly in the space of spike trains. The Schoenberg kernel maps the spike train to an RKHS and allows linear algorithm to control the nonlinear neural system without the danger of converging to local minima. During operation, the adaptation of the controller minimizes a difference defined in the spike train RKHS between the system and the target response and keeps the inverse controller close to the inverse of the current neural circuit, which enables adapting to neural perturbations. The results on a realistic synthetic neural circuit show that the inverse controller based on the Schoenberg kernel outperforms the decoding accuracy of other models based on the conventional rate representation of neural signal (i.e., spikernel and generalized linear model). Moreover, after a significant perturbation of the neuron circuit, the control scheme can successfully drive the elicited responses close to the original target responses. [ABSTRACT FROM AUTHOR]

A new approach to vibration control simulation for electrodynamic shakers was developed using an electromagnetic finite element method (FEM) model. This approach consisted of two parts. First, the electromagnetic coupling FEM model of the shaker was developed using vibration theory and electromagnetic theory. The electromagnetic force was described using the Maxwell stress tensor, and the electromagnetic field distribution and the dynamic response of the shaker were calculated numerically using FEM. Second, the vibration control simulation system was established: the shaker was described using an electromagnetic FEM model, and the controller was described with an adaptive inverse algorithm. As an example, control simulation of a 1-ton electrodynamic shaker was conducted. The results demonstrate the validity of this approach and provide a basis for the controller design of electrodynamic shakers. [ABSTRACT FROM AUTHOR]

Based on adaptive inverse control theory, combined with neural network, neural network adaptive inverse controller is developed and applied to an electro-hydraulic servo system. The system inverse model identifier is constructed by neural network. The task is accomplished by generating a tracking error between the input command signal and the system response. The weights of the neural network are updated by the error signal in such a way that the error is minimized in the sense of mean square using (LMS) algorithm and the neural network is close to the system inverse model. The above steps make the gain of the serial connection system close to unity, realizing waveform replication function in real-time. To enhance its convergence and robustness, the normalized LMS algorithm is applied. Simulation in which nonlinear dead-zone is considered and experimental results demonstrate that the proposed control scheme is capable of tracking desired signals with high accuracy and it has good real-time performance. [ABSTRACT FROM PUBLISHER]

A combined control strategy with an adaptive inverse control (AIC) and an inverse frequency response function (IFRF) equalization technique is proposed for the electrohydraulic shaking table (EST) system. The control purpose is to improve the accuracy of time waveform replication. In contrast to the iterative compensation through repetitive excitations control approach of industrial EST controllers, the proposed control strategy utilizes an IFRF of the EST system for extending the EST system frequency bandwidth and obtaining asymptotic reference tracking, and employs a variable tap-length filtered-x least-mean-squares algorithm to adaptively tune the time-domain drive signal and further improve the position and acceleration tracking performance of the EST system. Thus, the proposed combined control strategy is designed to combine the merits of IFRF and AIC. The procedures of the proposed control strategy are programmed in MATLAB/Simulink, and then compiled to a real-time PC with Microsoft Visual Studio.NET for implementation. The simulated and experimental results show that this control strategy achieves satisfactory position and acceleration waveform replication accuracy. [ABSTRACT FROM PUBLISHER]

An electro-hydraulic shaking table (EHST) is used for real-time replication of situations that occur in civil and architectural engineering, the automotive industry, and earthquake resistance testing. EHSTs are able to generate a large force at high speeds over a wide frequency range and this feature makes them invaluable in performing vibration tests. Unfortunately, due to the inherent dynamics of the EHST system’s hydraulics, the output response of an EHST system displays magnitude attenuation and phase delays in response to displacement and acceleration commands. A feedforward inverse model (FFIM) combined with adaptive inverse control (AIC) is proposed to improve the tracking performance of the EHST following specified displacement and acceleration commands. The proposed control strategy utilizes a FFIM to extend the EHST system’s frequency bandwidth and uses AIC based on a recursive least squares (RLS) algorithm to adaptively adjust the time domain drive signal of the EHST servo controller and improve the tracking accuracy. Experimental and simulation results demonstrate the effectiveness of the proposed combined control strategy. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents an approach to adaptive trajectory tracking of mobile robots which combines a feedback linearization based on a nominal model and a RBF-NN adaptive dynamic compensation. For a robot with uncertain dynamic parameters, two controllers are implemented separately: a kinematics controller and an inverse dynamics controller. The uncertainty in the nominal dynamics model is compensated by a neural adaptive feedback controller. The resulting adaptive controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance with a small computational effort. The analysis of the RBF-NN approximation error on the control errors is included. Finally, the performance of the control system is verified through experiments. [Copyright &y& Elsevier]

To deal with the difficulties in confirming the structure of neuron model and low forecast accuracy of grey theory, the grey situation decision theory based on new effect measure is proposed for the first time, and it is adopted to construct the structure topology of neural networks and determine the number of neurons in various layers and input-output computation of neurons. Then the grey neural network is taken as adaptive predictive inverse controller, which is implemented to the active control of jacket offshore platform. The simulation results show that the obtained grey neural network has strong robustness, and thus can be used to effectively control the displacement response on the top of jacket offshore platform under the random loads. [ABSTRACT FROM AUTHOR]

Random vibration control is aimed at reproducing the power spectral density (PSD) at specified control points. The classical frequency-spectrum equalization algorithm needs to compute the average of the multiple frequency response functions (FRFs), which lengthens the control loop time in the equalization process. Likewise, the feedback control algorithm has a very slow convergence rate due to the small value of the feedback gain parameter to ensure stability of the system. To overcome these limitations, an adaptive inverse control of random vibrations based on the filtered-X least mean-square (LMS) algorithm is proposed. Furthermore, according to the description and iteration characteristics of random vibration tests in the frequency domain, the frequency domain LMS algorithm is adopted to refine the inverse characteristics of the FRF instead of the traditional time domain LMS algorithm. This inverse characteristic, which is called the impedance function of the system under control, is used to update the drive PSD directly. The test results indicated that in addition to successfully avoiding the instability problem that occurs during the iteration process, the adaptive control strategy minimizes the amount of time needed to obtain a short control loop and achieve equalization. [ABSTRACT FROM AUTHOR]

Abstract: Single-track hard disk drive (HDD) seek performance is measured by settle time, , defined as the time from the arrival of a seek command until the measured position reaches and stays within an acceptable distance from the target track. Our previous work has shown feedforward dynamic inversion, coupled with an aggressive desired trajectory , is capable of achieving high performance settle times when the closed-loop dynamics are time-invariant and accurately modeled. In contrast, we describe an adaptive inversion procedure in this paper which removes the requirement for accurate initial models and tracks the position-variant dynamics present in our Servo Track Writer (STW) experimental apparatus. The proposed indirect adaptive inversion algorithm relies on a recursive least squares (RLS) estimate of the closed-loop dynamics. Pre-filtering of the RLS input signals, covariance resetting, and relative NMP system partitioning are necessary additions to the baseline adaptive algorithm in order to achieve fast settle times. Compared to the nonadaptive solution with accurate system identification, we show the adaptive algorithm achieves a 22% reduction in average settle time and a 53% reduction in settle time standard deviation. [Copyright &y& Elsevier]

This paper proposes a new method of adaptive inverse control based on support vector machine–fuzzy rules acquisition system (SVM-FRAS) for the gas tungsten arc welding (GTAW) process. In this control mechanism, an identifier is established based on SVM-FRAS, and an inverse controller based on SVM-FRAS is designed. The proposed adaptive inverse control method can automatically extract control rules from the process data. Comprehensibility is one of the required characteristics for a complex GTAW process control. We use the proposed SVM-FRAS-based adaptive inverse control method to obtain the rule-based process and the control model of the aluminum alloy pulse GTAW process. Based on the simulation experiments for GTAW process, the SVM-FRAS adaptive inverse control method is found to be effective. [ABSTRACT FROM AUTHOR]

This paper presents a new robust adaptive inverse control approach for a force-reflecting teleoperation system with varying time delay. First, an impedance control is designed for the master robot. Second, an adaptive inverse control is proposed for the slave robot. Finally, the slave side controller is modified such that the robust stability and performance are achieved. In addition, robust stability analysis has been performed and optimal behavior is ensured by using standard characteristic polynomials. It is shown that despite of presence of randomly-varying time delay, the proposed control algorithm compensates the position drifts efficiently. Demonstrable simulation studies confirm the effectiveness of the proposed control system and its advantages over the existing sliding mode control strategies. [ABSTRACT FROM AUTHOR]

A new modeling approach for nonlinear systems with rate-dependent hysteresis is proposed. The approach is used for the modeling of the giant magnetostrictive actuator, which has the rate-dependent nonlinear property. The models built are simpler than the existed approaches. Compared with the experiment result, the model built can well describe the hysteresis nonlinear of the actuator for input signals with complex frequency. An adaptive direct inverse control approach is proposed based on the fuzzy tree model and inverse learning and special learning that are used in neural network broadly. In this approach, the inverse model of the plant is identified to be the initial controller firstly. Then, the inverse model is connected with the plant in series and the linear parameters of the controller are adjusted using the least mean square algorithm by on-line manner. The direct inverse control approach based on the fuzzy tree model is applied on the tracing control of the actuator by simulation. The simulation results show the correctness of the approach. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive sliding mode control with hysteresis compensation-based neuroevolution (ACNE) is proposed for precise motion tracking of the piezoelectric actuator (PEA) in the presence of uncertainties, disturbances, and nonlinearity hysteresis characteristics. Firstly, a new memetic differential evolution (MeDE) algorithm is proposed to optimize the weights of a 3-layer n eural network (called n euro e volution or NE). In MeDE, a differential evolution algorithm is used as a global search scheme and the Jaya algorithm is used as local search exploitation. Secondly, an inverse hysteresis model of PEA is identified by the neuroevolution model to provide a feed-forward NE control signal to compensate for the hysteresis behavior of PEA system. Thirdly, an adaptive neural sliding mode control plus feedforward NE (ACNE) control is designed to enhance the quality control and guarantee asymptotical stability for PEA system. Based on the Lyapunov method, the stability of the closed-loop system is analyzed and proved. Finally, the experimental Thorlabs piezoelectric actuator (PEA) is set up to verify the robustness and effectiveness of the proposed approach. Results show that the identified MeDE-Neuroevolution model has successfully applied to model the inverse hysteretic of PEA system and the performance of MeDE has better than Jaya, DE, and PSO in terms of best, worst, average, and standard deviation. Furthermore, in motion tracking control, the performance of proposed ACNE control has more accurate than a classical PID control, a feedforward control, a hybrid feedback–feedforward control, and an adaptive neural sliding mode control without a compensator. • A new adaptive inverse neural (AIN) control method is applied to precisely tracking of PZT actuator displacement. • A 3-layer neural model optimized by EDE technique is used to identify the inverse hysteresis structure of PZT. • A feed-forward control using the identified model is proposed to compensate for the PZT hysteresis effects. • Lyapunov principle is used to implement an adaptive law based neural sliding mode plus feed-forward compensator to ensure PZT plant operated in stability. • Experiment results demonstrate the superiority of proposed AIN approach in comparison with other advanced control methods. [ABSTRACT FROM AUTHOR]

Adaptive inverse control system can improve the performance of turbo decoding, and modeling turbo decoder is one of the most important technologies. A neural network model for the inverse model of turbo decoding is proposed in this paper. Compared with linear filter with its revision, the general relationship between the input and output of the inverse model of turbo decoding system can be established exactly by Nonlinear Auto-Regressive eXogeneous input (NARX) filter. Combined with linear inverse system, it has simpler structure and costs less computation, thus can satisfy the demand of real-time turbo decoding. Simulation results show that neural network inverse control system can improve the performance of turbo decoding further than other linear control system. [ABSTRACT FROM AUTHOR]

This paper deals with the adaptive control of a class of continuous-time non-linear dynamic systems preceded by unknown non-symmetrical, non-equal slope dead-zones. By exploring the properties of the dead-zone model intuitively and mathematically, a dead-zone inverse is constructed. Based on this inverse construction, an adaptive sliding controller is designed. Lyapunov stability analysis shows that the proposed adaptive control law ensures global stability of the adaptive system and achieves desired tracking precision. Simulation results attained for an uncertain non-linear system are presented to illustrate and further validate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper presents investigations into the development of adaptive inverse-dynamic and neuro-inverse-dynamic control strategies for a flexible manipulator system employing a combined collocated and non-collocated control structure. Collocated control is utilized to track the position of the system while the non-collocated inverse and neuro-inverse control are utilized to reduce the vibration of the system. The controllers are developed in two phases: a collocated position control loop using proportional–derivative feedback control is developed and combined first with an adaptive inverse non-collocated control loop using a recursive least-squares algorithm and then with a neuro-inverse model using a multi-layered perceptron neural network. The problem of instability of the non-collocated control loop arising from the non-minimum phase characteristics of the plant is solved in the former case by reflecting the non-invertible plant zeros into the stability region. In the case of the neuro-inverse model, the problem of instability of the control loop is accounted for through the neuro-inverse learning process. The performances of both the proposed control strategies are assessed within a simulation environment of a single-link flexible manipulator and it is demonstrated that a significant reduction in the level of structural vibration of the system is achieved with both techniques. The significance of the neuro-inverse model approach in achieving stable control is demonstrated. [ABSTRACT FROM AUTHOR]