Search

Real‐time selective protein quantification is an integral component of operating continuous chromatography processes. Partial least squares models fit with spectroscopic UV‐Vis absorbance data have demonstrated the ability to selectively quantify proteins. With standard continuous chromatography equipment that is only capable of measuring absorbance at a few user‐defined wavelengths, the problem of selecting appropriate wavelengths that maximize the measurement capability of the instrument remains unaddressed. Therefore, we propose a method for selecting wavelengths for continuous chromatography equipment. We illustrate our method using sets of protein mixtures composed of bovine serum albumin and lysozyme. The first step is to refine the raw wavelength set with a statistical t‐test and an absorbance magnitude test. Then, the wavelengths within the refined spectroscopic range are ranked. Three existing techniques are evaluated – sequential forward search, variable importance to projection scores, and the least absolute shrinkage and selection operator. The best technique (in this case, sequential forward search) determines a subset of three wavelengths for further evaluation on the BioSMB PD. We use an exhaustive approach to determine the final wavelength set. We show that soft sensor models trained from the method's wavelength selections can quantify the two proteins more accurately than from the wavelength set of 230, 260 and 280 nm, by a factor of four. The method is shown to determine appropriate wavelengths for different path lengths and protein concentration ranges. Overall, we provide a tool that alleviates the analytical bottleneck for practitioners seeking to develop advanced monitoring and control methods on standard equipment. Application of a wavelength selection method that consists of a spectroscopic wavelength refinement step, followed by a wavelength ranking step and then a final wavelength verification step using in‐line absorbance data. The soft sensor partial least square models trained from the method's wavelength selections can selectively quantify proteins more accurately than from a set of 230, 260, and 280 nm wavelengths. The proposed method is shown to generate appropriate wavelengths for data sets of different path length and concentration ranges. [ABSTRACT FROM AUTHOR]

The present article enables reinforcement learning (RL)‐based controllers for process control applications. Existing instances of RL‐based solutions have significant challenges for online implementation since the training process of an RL agent (controller) presently requires practically impossible number of online interactions between the agent and the environment (process). To address this challenge, we propose an implementable model‐free RL method developed by leveraging industrially implemented model predictive control (MPC) calculations (often designed using a simple linear model identified via step tests). In the first step, MPC calculations are used to pretrain an RL agent that can mimic the MPC performance. Specifically, the MPC calculations are used to pretrain the actor, and the objective function is used to pretrain the critic(s). The pretrained RL agent is then employed within a model‐free RL framework to control the process in a way that initially imitates MPC behavior (thus not compromising process performance and safety), but also continuously learns and improve its performance over the nominal linear MPC. The effectiveness of the proposed approach is illustrated through simulations on a chemical reactor example. [ABSTRACT FROM AUTHOR]

This manuscript addresses the problem of controlling a bioreactor to maximize the production of a desired product while respecting the constraints imposed by the nature of the bio‐process. The approach is demonstrated by first building a data‐driven model and then formulating a model predictive controller (MPC) with the results illustrated by implementing a detailed monoclonal antibody production model (the test bed) created by Sartorius Inc. In particular, a recently developed data‐driven modelling approach using an adaptation of subspace identification techniques is utilized that enables the incorporation of known physical relationships in the data‐driven model development (constrained subspace model identification), making the data‐driven model process aware. The resultant controller implementation demonstrates a significant improvement in production compared to the existing proportional integral (PI) controller strategy used in the monoclonal antibody production. Simulation results also demonstrate the superiority of the process‐aware or constrained subspace MPC compared to traditional subspace MPC. Finally, the robustness of the controller design is illustrated via the implementation of a model developed using data from a test bed with a different set of parameters, thus showing the ability of the controller design to maintain good performance in the event of changes such as a different cell line or feed characteristics. [ABSTRACT FROM AUTHOR]

The present paper addresses the problem of designing a controller to enable stabilisation from the entire null controllable region (NCR) – the set of states from where stabilisation is possible). A recently developed approach for the numerical construction of the NCR is utilised, and first, the validity of the use of the NCR as a constrained control Lyapunov function (CCLF) is established. The analysis reveals the ability of a CCLF-based control design to drive the system to an equilibrium manifold. The CCLF-based control design is then utilised within a hybrid control framework that guarantees the ability to stabilise to the origin. Simulation results are used to illustrate the implementation of the control design. [ABSTRACT FROM AUTHOR]

The prevalence of batch and batch-like operations, in conjunction with the continued resurgence of artificial intelligence techniques for clustering and classification applications, has increasingly motivated the exploration of the applicability of deep learning for modeling and feedback control of batch and batch-like processes. To this end, the present study seeks to evaluate the viability of artificial intelligence in general, and neural networks in particular, toward process modeling and control via a case study. Nonlinear autoregressive with exogeneous input (NARX) networks are evaluated in comparison with subspace models within the framework of model-based control. A batch polymethyl methacrylate (PMMA) polymerization process is chosen as a simulation test-bed. Subspace-based state-space models and NARX networks identified for the process are first compared for their predictive power. The identified models are then implemented in model predictive control (MPC) to compare the control performance for both modeling approaches. The comparative analysis reveals that the state-space models performed better than NARX networks in predictive power and control performance. Moreover, the NARX networks were found to be less versatile than state-space models in adapting to new process operation. The results of the study indicate that further research is needed before neural networks may become readily applicable for the feedback control of batch processes. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of system identification for heating, ventilation, and air conditioning (HVAC) systems using a relatively small amount of data for the zone under consideration, by leveraging larger datasets for similar zones. To this end, a hybrid machine learning approach is developed where a pre‐trained recurrent neural network (RNN) model, trained on a large amount of data from a representative zone, is leveraged to build models for the other zones using a smaller amount of data. This is achieved by developing a hybrid model that integrates the pre‐trained RNN model with the models built using the subspace identification (SubID) technique to predict the residuals (differences between the real outputs and the predicted outputs from the pre‐trained RNN model) in the other zones. The effectiveness of the proposed hybrid approach is shown using real data collected from a multi‐zone fitness centre. The results demonstrate the superior performance of the hybrid approach over the cases where individual RNN and SubID models are directly developed using only the data from the zones in question. [ABSTRACT FROM AUTHOR]