Continuous manufacturing offers potential opportunities for the improved manufacturing of pharmaceutical products. A key challenge is the development of an appropriate control strategy.The experimental application of an automated control strategy is presented for an end-to-end continuous pharmaceutical pilot plant. The process starts from an advanced intermediate compound and finishes with the tablet formation steps. The focus of the experimental results is on the design and performance of the control loops needed to produce a slurry of an active pharmaceutical ingredient and a solvent with specified material properties. The results demonstrate that automated control can successfully keep critical material attributes close to desired set points for a sustained period of operation. This work aims to contribute to the

The bearingless induction motor (BLIM) is a multi-variable, non-linear, strong coupling system. To achieve higher performance control, a novel neural network inverse system decoupling control strategy considering stator current dynamics is proposed. Taking the stator current dynamics of the torque windings into account, the state equations of the BLIM system is established first. Then, the inverse system model of the BLIM is identified by a three-layer neural network; by means of the neural network inverse system method, the BLIM system is decoupled into four independent second-order linear subsystems, include a rotor flux subsystem, a motor speed subsystem and two radial displacement component subsystems. On this basis, the neural network inverse decoupling control system is constructed, the simulation verification and analyses are performed. From the simulation results, it is clear that when the proposed decoupling control strategy is adopted, not only can the dynamic decoupling control between relevant variables be achieved, but the control system has a stronger anti-load disturbance ability, smaller overshoot and better tracking performance.

The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains: (i) VOT-ST2021 challenge focused on short-term tracking in RGB, (ii) VOT-RT2021 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2021 focused on long-term tracking, namely coping with target disappearance and reappearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 introduces a training dataset and sequestered dataset for winner identification. The source code for most of the trackers, the datasets, the evaluation kit and the results along with the source code for most trackers are publicly available at the challenge website 1 .

The judicious use of buffering capacity is important in the development of future continuous pharmaceutical manufacturing processes. The potential benefits are investigated of using optimal-averaging level control for tanks that have buffering capacity for a section of a continuous pharmaceutical pilot plant involving two crystallizers, a combined filtration and washing stage and a buffer tank. A closed-loop dynamic model is utilized to represent the experimental operation, with the relevant model parameters and initial conditions estimated from experimental data that contained a significant disturbance and a change in setpoint of a concentration control loop. The performance of conventional proportional-integral (PI) level controllers is compared with optimal-averaging level controllers. The aim is to reduce the production of off-spec material in a tubular reactor by minimizing the variations in the outlet flow rate of its upstream buffer tank. The results show a distinct difference in behavior, with the optimal-averaging level controllers strongly outperforming the PI controllers. In general, the results stress the importance of dynamic process modeling for the design of future continuous pharmaceutical processes

No abstract

No abstract

No abstract

No abstract