Design and analysis of ELM-based predefined time sliding mode adaptive controller for PMLM position control under physical constraints.

Achieving accurate position tracking for robotics and industrial servo systems is an extremely challenging task, particularly when dealing with control saturation, parameter perturbation, and external disturbance. To address these challenges, a predefined time convergent sliding mode adaptive controller (PTCSMAC) has been proposed for a permanent magnet linear motor (PMLM). A novel sliding mode surface (SMS) with predefined time convergence PDTC has been constructed, which ensures that the error converges to zero within the prescribed time. The system not only meets the expected performance standards but also has a uniformly bounded motor speed. The trajectory tracking error in SMS is proven to converge to zero within the predefined time. This predefined time stability of the closed-loop system has been demonstrated by using the Lyapunov stability criterion with PDTC. The convergence time (CT) can be arbitrarily set, and the upper bound of it is not affected by the initial value and control parameters of the system. A new updated version of extreme learning machine (ELM) is introduced to approximate the uncertain part of the system based on PDTC. The ELM is also provided with the hyperbolic tangent function to estimate the saturation constraint. This is done by converting the function into a linear function concerning the unconstrained control input variable. Then, based on established stability, a novel sliding mode adaptive controller (PTCSMAC) with predefined time convergence is designed. The convergence time (CT) of the controller is unaffected by the initial conditions as well as the control parameters. The rigorous numerical simulations on the PMLM model with complex disturbances verify the strong robustness and high-precision tracking characteristic of the proposed control law.

An adaptive predefined time sliding mode control for uncertain nonlinear cyber-physical servo system under cyber attacks.

Malicious attacks are often inevitable in cyber-physical systems (CPS). Accuracy in Cyber physical system for position tracking of servos is the major concern now a days. In high precision industrial automation, it is very hard to achieve accuracy in tracking especially under malicious cyber-attacks, control saturations, parametric perturbations and external disturbances. In this paper, we have designed a novel predefined time (PDT) convergence sliding mode adaptive controller (PTCSMAC) for such kind of cyber physical control system. Main key feature of our control is to cope these challenges that are posed by CPS systems such as parameter perturbation, control saturation, and cyber-attacks and the whole system then upgrade to a third-order system to facilitate adaptive control law. Then, we present an adaptive controller based on the novel PDT convergent sliding mode surface (SMS) combined with a modified weight updated Extreme Learning Machine (ELM) which is used to approximate the uncertain part of the system. Another significant advantage of our proposed control approach is that it does not require detailed model information, guaranteeing robust performance even when the system model is uncertain. Additionally, our proposed PTCSMAC controller is nonsingular regardless of initial conditions, and is capable of eradicating the possibility of singularity problems, which are frequently a concern in numerous CPS control systems. Finally, we have verified our designed PTCSMAC control law through rigorous simulations on CPS seeker servo positioning system and compared the robustness and performance of different existing techniques.

Adaptive fuzzy-based stability control and series impedance correction for the grid-tied inverter.

The regenerative braking in the tram allows the energy to be returned to the power grid through a power inverter. Since the inverter location between the tram and the power grid is not fixed, resulting in a wide variety of impedance networks at grid coupling points, posing a severe threat to the stable operation of the grid-tied inverter (GTI). By independently changing the loop characteristics of the GTI, the adaptive fuzzy PI controller (AFPIC) can adjust according to different impedance network parameters. It is challenging to fulfill the stability margin requirements of GTI under high network impedance since the PI controller has phase lag characteristics. A correction method of series virtual impedance is proposed, which connects the inductive link in a series configuration with the inverter output impedance, correcting the inverter equivalent output impedance from resistance-capacitance to resistance-inductance and improving the system stability margin. Feedforward control is adopted to improve the system's gain in the low-frequency band. Finally, the specific series impedance parameters are obtained by determining the maximum network impedance and setting the minimum phase margin of 45°. The realization of virtual impedance is simulated by conversion to an equivalent control block diagram, and the effectiveness and feasibility of the proposed method are verified by simulation and a 1 kW experimental prototype.

A novel adaptive PD-type iterative learning control of the PMSM servo system with the friction uncertainty in low speeds.

High precision demands in a large number of emerging robotic applications strengthened the role of the modern control laws in the position control of the Permanent Magnet Synchronous Motor (PMSM) servo system. This paper proposes a learning-based adaptive control approach to improve the PMSM position tracking in the presence of the friction uncertainty. In contrast to most of the reported works considering the servos operating at high speeds, this paper focuses on low speeds in which the friction stemmed deteriorations become more obvious. In this paper firstly, a servo model involving the Stribeck friction dynamics is formulated, and the unknown friction parameters are identified by a genetic algorithm from the offline data. Then, a feedforward controller is designed to inject the friction information into the loop and eliminate it before causing performance degradations. Since the friction is a kind of disturbance and leads to uncertainties having time-varying characters, an Adaptive Proportional Derivative (APD) type Iterative Learning Controller (ILC) named as the APD-ILC is designed to mitigate the friction effects. Finally, the proposed control approach is simulated in MATLAB/Simulink environment and it is compared with the conventional Proportional Integral Derivative (PID) controller, Proportional ILC (P-ILC), and Proportional Derivative ILC (PD-ILC) algorithms. The results confirm that the proposed APD-ILC significantly lessens the effects of the friction and thus noticeably improves the control performance in the low speeds of the PMSM.

Duplex PD inertial damping control paradigm for active power decoupling of grid-tied virtual synchronous generator.

The growth of distributed generation significantly reduces the synchronous generators' overall rotational inertia, causing large frequency deviation and leading to an unstable grid. Adding virtual rotational inertia using virtual synchronous generators (VSG) is a promising technique to stabilize grid frequency. Due to coupled nature of frequency and active output power in a grid-tied virtual synchronous generator (GTVSG), the simultaneous design of transient response and steady state error becomes challenging. This paper presents a duplex PD inertial damping control (DPDIDC) technique to provide active power control decoupling in GTVSG. The power verses frequency characteristics of GTVSG is analyzed emphasizing the inconsistencies between the steady-state error and transient characteristics of active output power. The two PD controllers are placed in series with the generator's inertia forward channel and feedback channel. Finally, the performance superiority of the developed control scheme is validated using a simulation based study.

Supervised ensemble learning methods towards automatically filtering Urdu fake news within social media.

The popularity of the internet, smartphones, and social networks has contributed to the proliferation of misleading information like fake news and fake reviews on news blogs, online newspapers, and e-commerce applications. Fake news has a worldwide impact and potential to change political scenarios, deceive people into increasing product sales, defaming politicians or celebrities, and misguiding visitors to stop visiting a place or country. Therefore, it is vital to find automatic methods to detect fake news online. In several past studies, the focus was the English language, but the resource-poor languages have been completely ignored because of the scarcity of labeled corpus. In this study, we investigate this issue in the Urdu language. Our contribution is threefold. First, we design an annotated corpus of Urdu news articles for the fake news detection tasks. Second, we explore three individual machine learning models to detect fake news. Third, we use five ensemble learning methods to ensemble the base-predictors' predictions to improve the fake news detection system's overall performance. Our experiment results on two Urdu news corpora show the superiority of ensemble models over individual machine learning models. Three performance metrics balanced accuracy, the area under the curve, and mean absolute error used to find that Ensemble Selection and Vote models outperform the other machine learning and ensemble learning models.