This study proposes a multilayer hybrid deep-learning system (MHS) to automatically sort waste disposed of by individuals in the urban public area. This system deploys a high-resolution camera to capture waste image and sensors to detect other useful feature information. The MHS uses a CNN-based algorithm to extract image features and a multilayer perceptrons (MLP) method to consolidate image features and other feature information to classify wastes as recyclable or the others. The MHS is trained and validated against the manually labelled items, achieving overall classification accuracy higher than 90% under two different testing scenarios, which significantly outperforms a reference CNN-based method relying on image-only inputs.

In this article, the free-will arbitrary time consensus is formulated for multiagent systems. This consensus protocol is independent of initial conditions and any other system parameters. With such a protocol, the multiagent system is shown to attain consensus as well as average consensus within the prespecified arbitrary time. Agents rendezvous can also be accomplished with the given protocol. Communication imperfections are easily handled with the designed protocol. Robust free-will arbitrary time consensus protocol is also designed. The stability of such nonlinear nonautonomous protocols is established using suitable Lyapunov functions. Simulation examples confirm the theoretical findings.

This paper proposes new discrete-time algorithms of the super-twisting observer and the twisting controller to be applied to second-order systems. The algorithms are based on the full implicit-Euler discretization, which contributes to the elimination of chattering. Proofs of some stability properties of the discretized twisting controller are also provided. Simulations show that, as compared to traditional explicit-Euler schemes, the proposed scheme avoids the chattering both in trajectory tracking output and control input in the presence of external disturbances.

Finding and tracking maximum power point are two important dynamics in the control of variable speed wind turbines, since they determine the efficiency of wind turbines. The conventional hill climbing possesses the problems of wrong directionality and low performance, since it does not take the inertial effect into account. In this study, a novel hill climbing method is proposed by considering the inertial effect to solve these problems. Besides, employing the exact model knowledge of the generator in the maximum power tracking control deteriorates the efficiency considerably, therefore it is required to design a parameter independent and robust control system if possible. Thus, the third order super twisting sliding mode and continuous integral sliding mode controllers are designed for the control of generator and grid side converters to track the maximum power trajectory accurately, and they are compared to each other for the chattering in experimental results. A comparison is also performed between the conventional and proposed hill climbing methods based on the captured energy from the wind. Experimental results, with a wind turbine emulator, demonstrate that the proposed hill climbing method relaxes the wrong directionality and sluggish performance of the conventional one.

Predefined-time stability is the stability of dynamical systems whose solutions approach the equilibrium point within a pre-decided time duration. In this technical note, we develop general results of predefined-time stability of nonlinear systems using vector Lyapunov functions. A vector comparison system, which is predefined time convergent, is constructed, and after that the stability of the original dynamical system is proved using differential inequalities and comparison principles. Moreover, we design predefined-time controllers for large-scale systems using vector control Lyapunov functions (VCLFs). Sliding mode control is introduced in the design approach to mitigate matched bounded disturbances/uncertainties. Also, we aggregate comparison systems to reduce their dimensionality in order to effectively apply the derived results on practical systems. The theoretical results are implemented on a 2 DOF Helicopter model.

This article presents a solution to the problem of achieving optimal prescribed-time stability and stabilization for nonlinear dynamical systems. In contrast to existing prescribed-time control methods, this article initiates by establishing sufficient conditions for prescribed-time stability through the use of continuous Lyapunov candidate functions. Building upon these conditions, we introduce an optimal prescribed-time stabilization method that incorporates specific differential inequalities. This method complies with the Hamilton-Jacobi-Bellman steady-state equation, ensuring both optimality and prescribed-time stability. Furthermore, we derive a set of optimal prescribed-time stabilizing control laws for a class of affine nonlinear dynamical systems. Finally, we demonstrate the effectiveness of the proposed approach through simulations and experiments involving the reference level tracking of a coupled tank system, thus ensuring that the tracking performance aligns with practical user specifications Note to Practitioners —This article was instigated by the challenge of devising optimal feedback control strategies for a specific class of nonlinear dynamical systems at predetermined time instances. In recent years, there has been a growing interest in prescribed time stability and stabilization approaches, driven by their potential applications across diverse fields, including control engineering, robotics, and aerospace engineering. These methods facilitate the regulation of nonlinear dynamical systems to reach a desired steady state within a predefined finite time, offering a valuable solution for situations demanding rapid stabilization. In this article, we introduce a novel optimal prescribed-time stabilization method that relies on specific differential inequalities. This method not only adheres to the Hamilton-Jacobi-Bellman steady-state equation but also guarantees both optimality and prescribed-time stability. Furthermore, we derive a family of optimal prescribed-time stabilizing control laws tailored to a particular class of affine nonlinear dynamical systems. To validate the effectiveness of our proposed stabilization approach, we conduct experiments focusing on tracking the desired water level within a coupled tank system. Ultimately, the presented prescribed-time optimal feedback control strategy marks a significant stride forward in the advancement of optimal and efficient control methods for nonlinear dynamical systems, offering solutions that hold immense promise in practical applications.