Search
Search results for: BACKSTEPPING, NEURAL NETWORKS, RBF, DYNAMIC SHIP POSITIONING
-
Dynamically positioned ship steering making use of backstepping method and artificial neural networks
PublicationThe article discusses the issue of designing a dynamic ship positioning system making use of the adaptive vectorial backstepping method and RBF type arti cial neural networks. In the article, the backstepping controller is used to determine control laws and neural network weight adaptation laws. e arti cial neural network is applied at each time instant to approximate nonlinear functions containing parametric uncertainties....
-
Synteza układu sterowania statkiem morskim dynamicznie pozycjonowanym w warunkach niepewności
PublicationNiniejsza monografia obejmuje zagadnienia związane z syntezą układu dynamicznego pozycjonowania statku w środowisku morskim z zastosowaniem wybranych nieliniowych metod sterowania. W ramach pracy autorka rozważała struktury sterowania z zastosowaniem wektorowej adaptacyjnej metody backstep oraz metod jej pokrewnych, takich jak regulatory MSS (ang. multiple surface sliding), DSC (ang. dynamic surface control), NB (ang. neural backstepping)....
-
Dynamic Positioning System with Vectorial Backstepping Controller
PublicationThe problem of synthesis a dynamic positioning system for low frequency model of surface vessel was considered in this paper. The recursive vectorial backstepping control design was used to keep a fixed position and heading in presence of wave disturbances. The passive observer was introduced to smooth the measurements and to estimate the velocities needed for the control algorithm. Some parameters of observer were optimized off-line...
-
Control System Design for Dynamic Positioning using Vectorial Backstepping
PublicationThe problem of synthesis a dynamic positioning system for low frequency model of surface vessel was considered in this paper. The recursive vectorial backstepping control design was used to keep a fixed position and heading in presence of wave disturbances. The passive observer was introduced to smooth the measurements and to estimate the velocities needed for the control algorithm. The computer simulation results were given to...
-
Ship Dynamic Positioning Based on Nonlinear Model Predictive Control
PublicationThe presented work explores the simulation test results of using nonlinear model predictive control algorithm for ship dynamic positioning. In the optimization task, a goal function with a penalty was proposed with a variable prediction step. The results of the proposed control algorithm were compared with backstepping and PID. The effect of estimation accuracy on the control quality with the implemented algorithms was investigated....
-
Adaptive dynamic control allocation for dynamic positioning of marine vessel based on backstepping method and sequential quadratic programming
PublicationIt is generally assumed in dynamic positioning of over-actuated marine vessels that the control effectiveness matrix (input matrix) is known and constant, or, in case of fault information, it is estimated by the fault detection and diagnosis system. The purpose of the study is to develop the adaptive dynamic positioning control system for an over-actuated marine vessel in the presence of uncertainties and with emphasis on limited...
-
ANALYSIS OF IMPACT of SHIP model parameters on changes of control quality index in ship dynamic positioning system
PublicationIn this work there is presented an analysis of impact of ship model parameters on changes of control quality index in a ship dynamic positioning system designed with the use of a backstepping adaptive controller. Assessment of the impact of ship model parameters was performed on the basis of Pareto-Lorentz curves and ABC method in order to determine sets of the parameters which have either crucial, moderate or low impact on objective...
-
Dynamic Positioning Capability Assessment for Ship Design Purposes
PublicationThe article focuses on solving a problem of optimal thrust distribution over the actuators in a ship Dynamic Positioning, according to DNV-ST-0111 standard, Level 1. The classic Quadratic Programming approach is combined with the numerical solusion used to handle the propeller with the rudder constraints in the optimization task and the influence between thrusters and skeg. It is presented as an efficient method of minimizing the...
-
Adaptive dynamic control allocation for over-actuated dynamic positioning system based on backstepping method in case of thruster faults
PublicationThe objective of the research considered in this paper is dynamic positioning of a nonlinear over-actuated marine vessel in the presence of limited information about thruster forces. First, the adaptive backstepping method is used to estimate the input matrix which will compensate partial loss of actuator effectiveness in the presence of actuator dynamics. Then, the adaptive commanded virtual forces and moment are allocated into...
-
Ship Resistance Prediction with Artificial Neural Networks
PublicationThe paper is dedicated to a new method of ship’s resistance prediction using Artificial Neural Network (ANN). In the initial stage selected ships parameters are prepared to be used as a training and validation sets. Next step is to verify several network structures and to determine parameters with the highest influence on the result resistance. Finally, other parameters expected to impact the resistance are proposed. The research utilizes...
-
USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING SHIP FUEL CONSUMPTION
PublicationIn marine vessel operations, fuel costs are major operating costs which affect the overall profitability of the maritime transport industry. The effective enhancement of using ship fuel will increase ship operation efficiency. Since ship fuel consumption depends on different factors, such as weather, cruising condition, cargo load, and engine condition, it is difficult to assess the fuel consumption pattern for various types...
-
Data fusion of GPS sensors using Particle Kalman Filter for ship dynamic positioning system
PublicationDepending on standards and class, dynamically positioned ships make use of different numbers of redundant sensors to determine current ship position. The paper presents a multi-sensor data fusion algorithm for the dynamic positioning system which allows it to record the proper signal from a number of sensors (GPS receivers). In the research, the Particle Kalman Filter with data fusion was used to estimate the position of the vessel....
-
Applying artificial neural networks for modelling ship speed and fuel consumption
PublicationThis paper deals with modelling ship speed and fuel consumption using artificial neural network (ANN) techniques. These tools allowed us to develop ANN models that can be used for predicting both the fuel consumption and the travel time to the destination for commanded outputs (the ship driveline shaft speed and the propeller pitch) selected by the ship operator. In these cases, due to variable environmental conditions, making...
-
Fractional Order Dynamic Positioning Controller
PublicationImproving the performance of Dynamic Positioning System in such applications as station keeping, position mooring and slow speed references tracking requires improving the position and heading control precision. These goals can be achieved through the improvement of the ship control system. Fractional-order calculus is a very useful tool which extends classical, integer-order calculus and is used in contemporary modeling and control...
-
Olgun Aydin dr
PeopleOlgun Aydin finished his PhD by publishing a thesis about Deep Neural Networks. He works as a Principal Machine Learning Engineer in Nike, and works as Assistant Professor in Gdansk University of Technology in Poland. Dr. Aydin is part of editorial board of "Journal of Artificial Intelligence and Data Science" Dr. Aydin served as Vice-Chairman of Why R? Foundation and is member of Polish Artificial Intelligence Society. Olgun is...
-
Deep neural networks for data analysis
e-Learning CoursesThe aim of the course is to familiarize students with the methods of deep learning for advanced data analysis. Typical areas of application of these types of methods include: image classification, speech recognition and natural language understanding. Celem przedmiotu jest zapoznanie studentów z metodami głębokiego uczenia maszynowego na potrzeby zaawansowanej analizy danych. Do typowych obszarów zastosowań tego typu metod należą:...
-
Neural networks and deep learning
PublicationIn this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings...
-
DYNAMIC POSITIONING CAPABILITY ASSESSMENT BASED ON OPTIMAL THRUST ALLOCATION
PublicationThe article presents an efficient method of optimal thrust allocation over the actuators in a dynamically positioned ship, according to the DNV-ST-0111 standard, Level 1. The optimisation task is approximated to a convex problem with linear constraints and mathematically formulated as quadratic programming. The case study is being used to illustrate the use of the proposed approach in assessing the DP capability of a rescue ship....
-
Designing Particle Kalman Filter for Dynamic Positioning
PublicationThe article presents a comparative analysis of two variants of the Particle Kalman Filter designed by using two different ship motion models. The first filter bases only on the kinematic model of the ship and can be used in many types of vehicles, regardless of the vehicle dynamics model. The input value to the filter is the noisy position of the ship. The second filter makes use of the kinematic and dynamic models of the moving...
-
Approximation of Fractional Order Dynamic Systems Using Elman, GRU and LSTM Neural Networks
PublicationIn the paper, authors explore the possibility of using the recurrent neural networks (RNN) - Elman, GRU and LSTM - for an approximation of the solution of the fractional-orders differential equations. The RNN network parameters are estimated via optimisation with the second order L-BFGS algorithm. It is done based on data from four systems: simple first and second fractional order LTI systems, a system of fractional-order point...
-
NEURAL NETWORKS
Journals -
A Selection of Starting Points for Iterative Position Estimation Algorithms Using Feedforward Neural Networks
PublicationThis article proposes the use of a feedforward neural network (FNN) to select the starting point for the first iteration in well-known iterative location estimation algorithms, with the research objective of finding the minimum size of a neural network that allows iterative position estimation algorithms to converge in an example positioning network. The selected algorithms for iterative position estimation, the structure of the...
-
A survey of neural networks usage for intrusion detection systems
PublicationIn recent years, advancements in the field of the artificial intelligence (AI) gained a huge momentum due to the worldwide appliance of this technology by the industry. One of the crucial areas of AI are neural networks (NN), which enable commer‐ cial utilization of functionalities previously not accessible by usage of computers. Intrusion detection system (IDS) presents one of the domains in which neural networks are widely tested...
-
Dynamic variables limitation for backstepping control of induction machine and voltage source converter
PublicationDynamic variables limitation for backstepping control of induction machine and voltage source converter The paper presents the method of control of an induction squirrel-cage machine supplied by a voltage source converter. The presented idea is based on an innovative method of the voltage source converter control, consisting in direct joining of the motor control system with the voltage source rectifier control system. The combined...
-
Nonlinear Backstepping Ship Course Controller
PublicationStatek, jako obiekt sterowania charakteryzuje się nieliniową manewrową funkcją opisującą. Metoda backstepping jest jedną z metod, które mogą być wykorzystane w procesie projektowania nieliniowych układu sterowania kursem statków. Metoda została zastosowana w celu zaprojektowania dwóch konfiguracji nieliniowych regulatorów kursu.Regulatory zostały przebadane w układach regulacji kursu statku. Jedna z konfiguracji w fazie projektowania...
-
Cluster-Dependent Feature Selection for the RBF Networks
Publication -
AGENT-BASED APPROACH TO THE DESIGN OF RBF NETWORKS
Publication -
An Automated Method for Biometric Handwritten Signature Authentication Employing Neural Networks
PublicationHandwriting biometrics applications in e-Security and e-Health are addressed in the course of the conducted research. An automated graphomotor analysis method for the dynamic electronic representation of the handwritten signature authentication was researched. The developed algorithms are based on dynamic analysis of electronically handwritten signatures employing neural networks. The signatures were acquired with the use of the...
-
Comparative study of neural networks used in modeling and control of dynamic systems
PublicationIn this paper, a diagonal recurrent neural network that contains two recurrent weights in the hidden layer is proposed for the designing of a synchronous generator control system. To demonstrate the superiority of the proposed neural network, a comparative study of performances, with two other neural network (1_DRNN) and the proposed second-order diagonal recurrent neural network (2_DRNN). Moreover, to confirm the superiority...
-
Performance Analysis of Convolutional Neural Networks on Embedded Systems
PublicationMachine learning is no longer confined to cloud and high-end server systems and has been successfully deployed on devices that are part of Internet of Things. This paper presents the analysis of performance of convolutional neural networks deployed on an ARM microcontroller. Inference time is measured for different core frequencies, with and without DSP instructions and disabled access to cache. Networks use both real-valued and...
-
Analysis of data fusion algorithms for the vessel with the dynamic positioning system
PublicationThe dynamic positioning (DP) system on the vessel is operated to control the position and heading of the vessel with the use of propellers and thrusters installed on the board. On DP vessels redundant measurement systems of position, heading and the magnitude and direction of environmental forces are required for safety at sea. In this case, a fusion of data is needed from individual measurement devices. The article proposes a...
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublicationDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
Performance analysis of an rfid-based 3d indoor positioning system combining scene analysis and neural network methods
PublicationThe main purpose of this research is to improve localization accuracy of an active Radio Frequency Identification, RFID tag, in 3D indoor space. The paper presents a new RFID based 3D Indoor Positioning System which shows performance improvement. The proposed positioning system combines two methods: the Scene Analysis technique and Artificial Neural Network. The results of both simulation using Log-Distance Path Loss Model and...
-
Deep neural networks approach to skin lesions classification — A comparative analysis
PublicationThe paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine (SVM). The research was carried...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublicationIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
-
Gas Detection Using Resistive Gas Sensors And Radial Basis Function Neural Networks
PublicationWe present a use of Radial Basis Function (RBF) neural networks and Fluctuation Enhanced Sensing (FES) method in gas detection system utilizing a prototype resistive WO3 gas sensing layer with gold nanoparticles. We investigated accuracy of gas detection for three different preprocessing methods: no preprocessing, Principal Component Analysis (PCA) and wavelet transformation. Low frequency noise voltage observed in resistive gas...
-
Predicting the impact of traffic–induced vibrations on buildings using artificial neural networks
PublicationTraffic–induced vibrations may constitute a considerable load to a building, cause cracking of plaster, cracks in load–bearing elements or even a global structural collapse of the whole structure [1-4]. Vibrations measurements of real structures are costly and laborious, not justified in all cases. The aim of the paper is to create an original algorithm, to predict the negative dynamic impact on the examined residential building...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Clothes Detection and Classification Using Convolutional Neural Networks
PublicationIn this paper we describe development of a computer vision system for accurate detection and classification of clothes for e-commerce images. We present a set of experiments on well established architectures of convolutional neural networks, including Residual networks, SqueezeNet and Single Shot MultiBox Detector (SSD). The clothes detection network was trained and tested on DeepFashion dataset, which contains box annotations...
-
Outlier detection method by using deep neural networks
PublicationDetecting outliers in the data set is quite important for building effective predictive models. Consistent prediction can not be made through models created with data sets containing outliers, or robust models can not be created. In such cases, it may be possible to exclude observations that are determined to be outlier from the data set, or to assign less weight to these points of observation than to other points of observation....
-
A MODEL FOR FORECASTING PM10 LEVELS WITH THE USE OF ARTIFICIAL NEURAL NETWORKS
PublicationThis work presents a method of forecasting the level of PM10 with the use of artificial neural networks. Current level of particulate matter and meteorological data was taken into account in the construction of the model (checked the correlation of each variable and the future level of PM10), and unidirectional networks were used to implement it due to their ease of learning. Then, the configuration of the network (built on the...
-
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
PublicationBearing defect is statistically the most frequent cause of an induction motor fault. The research described in the paper utilized the phenomenon of the current change in the induction motor with bearing defect. Methods based on the analysis of the supplying current are particularly useful when it is impossible to install diagnostic devices directly on the motor. The presented method of rolling-element bearing diagnostics used indirect...
-
Neural modelling of dynamic systems with time delays based on an adjusted NEAT algorithm
PublicationA problem related to the development of an algorithm designed to find an architecture of artificial neural network used for black-box modelling of dynamic systems with time delays has been addressed in this paper. The proposed algorithm is based on a well-known NeuroEvolution of Augmenting Topologies (NEAT) algorithm. The NEAT algorithm has been adjusted by allowing additional connections within an artificial neural network and...
-
Neural Networks, Support Vector Machine and Genetic Algorithms for Autonomous Underwater Robot Support
PublicationIn this paper, artificial neural networks, a classification technique called support vector machine and meta-heuristics genetic algorithm have been considered for development in autonomous underwater robots. Artificial neural networks have been used for seabed modelling as well as support vector machine has been applied for the obstacles classification to avoid some collision problems. Moreover, genetic algorithm has been applied...
-
Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis
PublicationNumerous examples of physically unjustified neural networks, despite satisfactory performance, generate contradictions with logic and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage involves extending...
-
Designing RBF Networks Using the Agent-Based Population Learning Algorithm
Publication -
Cluster-dependent rotation-based feature selection for the RBF networks initialization
Publication -
Supply current signal and artificial neural networks in the induction motor bearings diagnostics
PublicationThis paper contains research results of the diagnostics of induction motor bearings based on measurement of the supply current with usage of artificial neural networks. Bearing failure amount is greater than 40% of all engine failures, which makes their damage-free operation crucial. Tests were performed on motors with intentionally made bearings defects. Chapter 2 introduces the concept of artificial neural networks. It presents...
-
A novel approach exploiting properties of convolutional neural networks for vessel movement anomaly detection and classification
PublicationThe article concerns the automation of vessel movement anomaly detection for maritime and coastal traffic safety services. Deep Learning techniques, specifically Convolutional Neural Networks (CNNs), were used to solve this problem. Three variants of the datasets, containing samples of vessel traffic routes in relation to the prohibited area in the form of a grayscale image, were generated. 1458 convolutional neural networks with...
-
Hybrid of Neural Networks and Hidden Markov Models as a modern approach to speech recognition systems
PublicationThe aim of this paper is to present a hybrid algorithm that combines the advantages ofartificial neural networks and hidden Markov models in speech recognition for control purpos-es. The scope of the paper includes review of currently used solutions, description and analysis of implementation of selected artificial neural network (NN) structures and hidden Markov mod-els (HMM). The main part of the paper consists of a description...