Feedforward motion control for unmeasured performance variables at the point of interest is crucial for attaining high throughput and accuracy in motion systems. The aim of this paper is to develop a data-driven approach for feedforward tuning that addresses the true performance at the point of interest. The presented approach is a novel methodology that employs rational feedforward structures for performing flexible tasks with high accuracy, in conjunction with an sensor fusion for addressing the point-of-interest. In particular, the tracking error of the unmeasured performance variable is accurately estimated by combining acceleration measurements and encoder measurements. Simulation results show that optimizing for the estimated point-of-interest error achieves similar tracking performance as optimizing for the true point-of-interest error, indicating accurate sensor-fusion estimates for feedforward control. Experimental validation demonstrates that optimizing for the estimated point-of-interest error significantly reduces the estimated point-of-interest tracking error compared to minimizing the encoder error.

Many industrial motion systems require performing a variety of tasks with high precision and safety. Iterative learning control (ILC) is a method with convergent update laws, generally classified into: 1) parametrized learning approach for achieving task-flexibility against varying tasks; or 2) signal-based learning approach which can achieve perfect tracking-performance for repeating tasks. The aim of this study is to join the distinct ILC frameworks, achieving all desirable properties in a single framework. Specifications on convergence, tracking-performance and task-flexibility of the developed joint parametrized/signal-based ILC are theoretically derived, confirmed with experimental results on a two-mass system.

The requirements for high accuracy and throughput in next-generation data-intensive motion systems lead to situations where position-dependent feedforward is essential. This article aims to develop a framework for interpretable and task-flexible position-dependent feedforward through systematic learning with automated experimental design. A data-driven and interpretable framework is developed by employing Gaussian process (GP) regression, enabling accurate modeling of feedforward parameters as a continuous function of position. The data is efficiently collected and illustrated through an iterative learning control (ILC) algorithm. Moreover, a framework for experimental design in the sense of automatically determining the training positions is presented by exploiting the uncertainty estimates of the GP and the specified first-principles knowledge. Two relevant case studies show the importance and significant performance improvement of the approach for position-dependent snap feedforward for a simplified 1-D wafer stage simulation and experimental application to position-dependent motor force constant compensation in an industrial wirebonder.

The performance of feedforward control depends strongly on its ability to compensate for reproducible disturbances. The aim of this paper is to develop a systematic framework for artificial neural networks (ANN) for feedforward control. The method involves three aspects: a new criterion that emphasizes the closed-loop control objective, inclusion of preview to deal with delays and non-minimum phase dynamics, and enabling the use of an iterative learning algorithm to generate training data in view of addressing generalization errors. The approach is illustrated through simulations and experiments on an industrial flatbed printer.

Feedforward control with task flexibility for MIMO systems is essential to meet the growing demands on throughput and accuracy of high-tech systems. The aim of this paper is to develop an experimentally efficient framework for data-driven tuning of rational feedforward controllers for general non-commutative MIMO systems. In the developed approach, the nonlinear terms in the non-convex optimisation problem of iterative learning control (ILC) are iteratively circumvented via approximation. This leads to a series of convex optimisation problems that can be solved offline to obtain the parameters of the rational feedforward controller. In addition, by limiting the number of offline iterations an experimentally intensive algorithm is derived, which could be beneficial in the case of severe model mismatch. A simulation study shows that the experimentally efficient approach converges fast through offline iterations and has improved convergence properties through the use of regularisation.

Cross-coupled iterative learning control (ILC) can improve the contour tracking performance of manufacturing systems significantly. This paper aims to develop a framework for norm-optimal cross-coupled ILC that enables intuitive tuning of time- and iteration-varying weights of the exact contour error and its tangential counterpart. This leads to an iteration-varying ILC algorithm for which convergence conditions are developed. In addition, a resource-efficient implementation is developed that reduces the computational load significantly and enables the use of long reference signals. The approach is experimentally validated on an industrial flatbed printer.

Feedforward control with task flexibility for MIMO systems is essential to meet ever-increasing demands on throughput and accuracy. The aim of this paper is to develop a framework for data-driven tuning of rational feedforward controllers in iterative learning control (ILC) for noncommutative MIMO systems. A convex optimization problem in ILC is achieved by rewriting the nonlinear terms in the control scheme as a function of the previous feedforward parameters. A simulation study on an multivariable industrial printer shows that the developed framework converges and achieves significant better performance than direct application of the RBF algorithm using SK-iterations for SISO systems.

The increasing demands on throughput and accuracy of semiconductor manufacturing equipment necessitates accurate feedforward motion control that includes compensation of input nonlinearities. The aim of this paper is to develop a data-driven feedforward approach consisting of a Wiener feedforward, i.e., linear parameterization with an output nonlinearity, to achieve high tracking accuracy and task flexibility for a class of Hammerstein systems. The developed approach exploits iterative learning control to learn a feedforward signal from data that minimizes the error and utilizes a control-relevant cost function to learn the parameters of a Wiener feedforward parameterization. Experimental validation on a wirebonder shows that the developed approach enables high tracking accuracy and task flexibility.

Advanced feedforward control methods enable mechatronic systems to perform varying motion tasks with extreme accuracy and throughput. The aim of this paper is to develop a data-driven feedforward controller that addresses input nonlinearities, which are common in typical applications such as semiconductor back-end equipment. The developed method consists of parametric inverse-model feedforward that is optimized for tracking error reduction by exploiting ideas from iterative learning control. Results on a simulated set-up indicate improved performance over existing identification methods for systems with nonlinearities at the input.

Feedforward control is essential to achieving good tracking performance in positioning systems. The aim of this paper is to develop an identification strategy for inverse models of systems with nonlinear dynamics of unknown structure using input-output data, which can be used to generate feedforward signals for a-priori unknown tasks. To this end, inverse systems are regarded as noncausal nonlinear finite impulse response (NFIR) systems, and modeled as a Gaussian Process with a stationary kernel function that imposes properties such as smoothness. The approach is validated experimentally on a consumer printer with friction and shown to lead to improved tracking performance with respect to linear feedforward.

Machine learning techniques, including Gaussian processes (GPs), are expected to play a significant role in meeting speed, accuracy, and functionality requirements in future data-intensive mechatronic systems. This paper aims to reveal the potential of GPs for motion control applications. Successful applications of GPs for feedforward and learning control, including the identification and learning for noncausal feedforward, position-dependent snap feedforward, nonlinear feedforward, and GP-based spatial repetitive control, are outlined. Experimental results on various systems, including a desktop printer, wirebonder, and substrate carrier, confirmed that data-based learning using GPs can significantly improve the accuracy of mechatronic systems.