This paper deals with the optimum dynamic positioning control problem for marine ships in presence of actuator gain uncertainties and unknown environmental disturbances. The proposed approach is formulated as two modules, i.e., guidance part part. By utilizing improved extremum seeking algorithm, optimum-seeking developed this note to generate reasonable heading ships. main purpose design ensure closed-loop system running efficiently environment-friendly practice. Combined principle, a...

Latent fault detection and diagnosis (LFDD) for equipment are crucial safety reliability in nuclear power reactors (NPRs). In this article, a high accuracy LFDD method combining gate recurrent unit-based autoencoder (GRU-AE) random forest (RF) was proposed control rod drive mechanisms (CRDM) pressurized water (PWRs). The movement sequences of the CRDM coils' current reflecting degradation were assumed as time series taken by sliding window. GRU-AE, network containing an encoder decoder,...

This study presents a new observer-based electronic line-shafting (ELS) control scheme as motion synchronisation solution for motor drives in the industrial manufacturing process. To achieve better speed performance each ac drive, sliding mode controller is proposed. designed based on non-linear reaching law, which helps to settle time/chattering dilemma conventional (SMC) approach. In addition, observer proposed estimate lumped disturbances drives. Disturbance estimation results are fed...

We investigate a weighted self-propelled agent system, wherein each agent's direction is determined by its spatial neighbors' directions with exponential weights according to the neighbor numbers. In order describe fact that some agents more neighbors might have larger influence on neighbors, we introduce scaling exponent of number between 0 and $\ensuremath{\infty}$. When equal 1, convergence efficiency enhanced in our simulation. Furthermore, as increases, i.e., effect weight becomes...

This paper presents a novel comperative value iteration (VI)-based adaptive dynamic programming method for multi-player differential game models with convergence proof. The players are divided into two groups in the learning process and adapt their policies sequentially. Our removes dependence of admissible initial policies, which is one main drawbacks PI-based frameworks. Furthermore, this algorithm enables to control without full knowledge others' system parameters or laws. efficacy our...

Maneuvering target tracking in wireless sensor networks (WSNs) has been a prominent research topic over the past twenty years. In many situations, WSNs are vulnerable to natural or man-made interference, resulting uncertainty problems. this paper, we propose an information-quality-based selection method with estimation feedback for maneuvering uncertain WSNs. First, based on Generalized Pseudo-Bayesian estimator of first order (GPB1) and unscented information filter (UIF), GPB1-UIF algorithm...

Ship detection in SAR images is a challenge and has traditionally been carried out using pixel based algorithms such as CFAR, this paper we use deep learning algorithm called YOLOv2 for the aforementioned task test its performance on three datasets, at different resolution quality, with two datasets DS1 DS2 consisting of over 400 high ship to image ratio, which consists raw, unfiltered third dataset DS3 full scale 5500 single lower resolution. High results are observed further improve once...

An adaptive consensus filter for sensor networks with unknown process and measurement noise statistics is proposed in this letter. The variational Bayes(VB) approach exploited to get local estimates of covariances prior inverse Wishart distributions. A distributed averaging on exponential-class densities applied the natural parameters predicted error covariance. Consensus measurements performed parallel two outcomes are fused. Simulation results demonstrate effectiveness compared...

In pattern recognition, feature selection aims to choose the smallest subset of features that is necessary and sufficient describe target concept. this paper, a mutual information-based constructive criterion under arbitrary information distributions input presented for selection. This can capture both relevance output classes redundancy with respect already-selected without any parameters like ß in MIFS or MIFS-U methods be preset. Furthermore, modified greedy algorithm called MICC...

An event-triggered consensus filter is proposed in this letter for state estimation distributed sensor networks based on the hybrid measurement and information scheme. For bandwidth reduction energy saving, an transmission strategy developed which each node selectively transmits only most relevant data so as to reduce while preserving filtering performance. Two different tests are performed parallel, respectively prior likelihood pair, evaluate loss (measured terms of Kullback-Leibler...