Hamid Khodabandehlou

The biopharmaceutical industry continuously seeks to optimize the critical quality attributes to maintain the reliability and cost‐effectiveness of its products. Such optimization demands a scalable and optimal control strategy to meet the process constraints and objectives. This work uses a model predictive controller (MPC) to compute an optimal feeding strategy leading to maximized cell growth and metabolite production in fed‐batch cell culture processes. The lack of high‐fidelity physics‐based models and the high complexity of cell culture processes motivated us to use machine learning algorithms in the forecast model to aid our development. We took advantage of linear regression, the Gaussian process and neural network models in the MPC design to maximize the daily protein production for each batch. The control scheme of the cell culture process solves an optimization problem while maintaining all metabolites and cell culture process variables within the specification. The linear and nonlinear models are developed based on real cell culture process data, and the performance of the designed controllers is evaluated by running several real‐time experiments.

This study proposes using a wavelet neural network (WNN) with a feedforward component and a model predictive controller (MPC) for online nonlinear system identification and control over a communication network. The WNN performs the online identification of the nonlinear system. The MPC uses the model to predict the future outputs of the system over an extended prediction horizon and calculates the optimal future inputs by minimizing a controller cost function. A computationally efficient formulation for the controller is presented to reduce the computational complexity of the MPC for online implementation and Lyapunov theory is used to prove the stability of the MPC. The methodology is applied to the online identification and control of an unmanned autonomous vehicle. Simulation results show that the MPC with an extended prediction horizon can effectively control the system in the presence of fixed or random network delay.

The complexity of adaptive control of nonlinear time-varying systems requires the use of novel methods that have lower computational complexity as well as ensuring good performance under time-varying parameter changes. In this study, we use adaptive matching pursuit algorithm with wavelet bases for an online identification and control of the nonlinear system with time-varying parameters. We apply the proposed online identification and control scheme to two different benchmark examples of nonlinear system identification and control. Simulation results show that the proposed algorithm, using adaptive matching pursuit with wavelet bases, can effectively identify and control the nonlinear system even in presence of time-varying parameters.

The classification of anomalies or sudden changes in power networks versus normal abrupt changes or switching actions is essential to take appropriate maintenance actions that guarantee the quality of power delivery. This issue has increased in importance and has become more complicated with the proliferation of volatile resources that introduce variability, uncertainty, and intermittency in circuit behavior that can be observed as variations in voltage and current phasors. This makes diagnostics applications more challenging. This paper proposes using quotient gradient system (QGS) to train two-stage partially recurrent neural network to improve anomaly classification rate in power distribution networks using high-fidelity data from micro-phasor measurement units (PMUs). QGS is a systematic approach to finding solutions of constraint satisfaction problems. We transform the PMUs data from the power network into a constraint satisfaction problem and use QGS to train a neural network by solving the resulting optimization problem. Simulation results show that the proposed supervised classification method can reliably distinguish between different anomalies in power distribution networks. Comparison with other neural network classifiers shows that QGS trained networks provide significantly better classification. Sensitivity analysis is performed concerning the number of PMUs, reporting rates, noise level and early versus late data stream fusion frameworks.

This paper introduces a new method to train recurrent neural networks using dynamical trajectory-based optimization. The optimization method utilizes a projected gradient system (PGS) and a quotient gradient system (QGS) to determine the feasible regions of an optimization problem and search the feasible regions for local minima. By exploring the feasible regions, local minima are identified and the local minimum with the lowest cost is chosen as the global minimum of the optimization problem. Lyapunov theory is used to prove the stability of the local minima and their stability in the presence of measurement errors. Numerical examples show that the new approach provides better results than genetic algorithm and error backpropagation (EBP) trained networks.

In this paper, we study the identification of two challenging benchmark problems using neural networks. Two different global optimization approaches are used to train a recurrent neural network to identify two challenging nonlinear models, the cascaded tanks, and the Bouc-Wen system. The first approach, quotient gradient system (QGS), uses the trajectories of the nonlinear dynamical system to find the local minima of the optimization problem. The second approach, dynamical trajectory-based methodology, uses two different nonlinear dynamical systems to find the connected components of the feasible region and then searches the regions for local minima of the optimization problem. Simulation results show that both approaches effectively identify the model of the cascade tanks and the Bouc-Wen model.