Piotr Przystałka

Damage assessment in composite plates using fractional wavelet transform of modal shapes with optimized selection of spatial wavelets

Damage assessment is one of the crucial topics in the operation of structural elements made of polymers and polymeric composites. From the wide range of diagnostic methods and techniques the vibration-based damage evaluation seems to be effective, useful for application in industrial conditions and the low-cost. In order to improve the sensitivity of such class of methods the advanced signal processing techniques should be applied.` One of such techniques is the wavelet transform, which ensures the high sensitivity to the singularities in the measured vibration signals. The paper deals with a method for damage detection and localization in composite plates using the fractional discrete wavelet transform applied to the displacements of the modal shapes. The optimized selection of the parameters of spatial wavelets makes possible to improve the sensitivity of a proposed method. The presented studies cover the discussion on the various types of heuristic optimization algorithms that can be used for searching the best values of parameters of the fractional wavelet transform. The problem of selection of the most effective optimization algorithm, which allows to find the most suitable parameters of wavelets for the structural diagnostics of composite plates, is also considered. The method was tested on the data obtained from numerical experiments with various types of simulated single and multiple damages. Case studies were also conducted experimentally using non-destructive and non-invasive measurements of the displacements of modal shapes. The main advantages, difficulties and limitations of the presented method were discussed.

Behavior-based control system of a mobile robot for the visual inspection of ventilation ducts

The paper deals with the implementation of a behavior-based control and learning controller for autonomous inspection robots. The presented control architecture is designed to be used in the mobile robot (Amigo) for the visual inspection of ventilation systems. The main aim of the authors’ study is to propose a behavior-based controller with neural network-based coordination methods. Preliminary results are promising for further development of the proposed solution. The method has several advantages when compared with other competitive and/or co-operative approaches due to its robustness and modularity.

Methodology of neural modelling in fault detection with the use of chaos engineering

The paper deals with the problem of robust fault detection using recurrent neural networks and chaos engineering. The main part of the proposed approach is a locally recurrent neural network that is composed of complex dynamic neural units for which chaotic behaviour can be obtained. Selected global and local optimization methods are connected to have diphase strategies for training this kind of neural networks. And beyond this, chaos engineering is incorporated into both the evolutionary and simulated annealing algorithm in order to improve the efficiency of the tuning procedure. The problem of selecting the most relevant input variables is solved by means of extended Hellwig?s method of integral capacity of information. Criteria isolines and a sensitive-based method are used to identify the suitable architecture of a neural network. Moreover, the issue of stability analysis of neural models is also considered in this paper. Recurrence quantification analysis is proposed for residual evaluation in order to have the comprehensive methodology of neural model-based fault detection. The preliminary verification of the elaborated methodology in modelling tasks was carried out for both simulation and industrial data. The fundamental verification was conducted for the data made available within DAMADICS benchmark problem. The achieved results confirm the effectiveness of the proposed approach. Graphical abstractDisplay Omitted HighlightsNeural modelling using chaos engineering is proposed to be used for designing robust fault detection systems.The proposed locally recurrent neural network can be used to model chaotic or stochastic behaviours of a system.Recurrence quantification analysis is proposed for residual evaluation to have the comprehensive approach to fault detection.The capability of the proposed methodology is presented using simulation and industrial data.

Model-Based Fault Detection and Isolation Using Locally Recurrent Neural Networks

The increasing complexity of technological processes implemented in present industrial installations causes serious problems in the modern control system design and analysis. Chemical refineries, electrical furnaces, water treatments and other industrial plants are complex systems and in some cases cannot be precisely described by classical mathematical models. On the other hand, modern industrial systems are subject to faults in their components. Due to these facts, fault-tolerant control design using soft computing methods is gaining more and more attention in recent years. In this paper, the model-based approach to fault detection and isolation using locally recurrent neural networks is presented. The paper contains a numerical example that illustrates the performance of the proposed locally recurrent neural network with respect to other well-known neural structures.

Application of selected classification schemes for fault diagnosis of actuator systems

The paper presents the application of various classification schemes for actuator fault diagnosis in industrial systems. The main objective of this study is to compare either single or meta-classification strategies that can be successfully used as reasoning means in off-line as well as on-line diagnostic expert systems. The applied research was conducted on the assumption that only classic and well-practised classification methods would be adopted. The comparison study was carried out within the DAMADICS benchmark problem which provides a popular framework for confronting different approaches in the development of fault diagnosis systems.

Velocity Planning of an Electric Vehicle Using an Evolutionary Algorithm

This paper presents an approach to planning the driving velocity of an electric vehicle. As an object of study a prototype vehicle Mushellka has been chosen. It was built to take part in the Shell Eco-marathon competition. The competition took place in May 2012 and 2013. The paper presents the results of the determined optimum velocity for the street circuit in Rotterdam. Optimizations were performed using evolutionary algorithms. The objective function was to minimize the energy consumption. The calculations were performed in Matlab Simulink. The paper describes the mathematical modelling of the vehicle, the idea and the method of route planning, as well as the use of a prototype telematic system.

Mobile robot for inspecting ventilation ducts

The paper deals with a concept and design of a mobile robot capable of inspecting ventilation ducts made of steel sheet. The robot can operate in several modes including: autonomous, manual, and training one. Some subsystems are briefly outlined. Mobility of the robot is achieved by four wheels that include permanent magnets. There are 2 DOFs associated to each wheel. The detection system assesses the internal state of the robot and its subsystems, and perceives the surrounding environment, providing the control system with vital data that allows completing inspection tasks. The robot is also equipped with environment recognition system that collects data whose meaning is twofold. Primarily, it allows assessing actual condition of the ducts being inspected. Further on, the data makes possible creating plans of long-term movements that are required in order to complete the mission. The work of all these systems is coordinated by the control system. It is based on behaviors that are selected or combined by a neural controller. The controller is able to learn better behaviors from examples. These issues are discussed in details in other papers presented at this event.

Structural Diagnostics of Composite Beams Using Optimally Selected Fractional B-spline Wavelets

The method of structural diagnostics of composite structures presented in this paper is based on discrete wavelet transform of displacements of modal shapes with usage of fractional B-spline wavelets. An application of such wavelets makes possible to improve the sensitivity of the method, which allows for detection and identification of even small damages occurred in the structure. In order to select the most sensitive wavelet bases for the analysis the optimization study was carried out, where the highest ratio of peak, which indicated the damage, to other values of detail coefficients and possibly short support of a peak in the location of the damage were chosen as the optimization criteria. Obtained results allow for the evaluation of the possible best wavelet bases for the damage identification of one-dimensional composite structures.

Environment detection and recognition system of a mobile robot for inspecting ventilation ducts

The system of environment detection and recognition is a part of a mobile robot. The task of the robot is to inspect ventilation ducts. The paper deals with elaborated methods of data and image transmission, image processing, analysis and recognition. While developing the system numerous approaches to different methods of lighting and image recognition were tested. In the paper there are presented results of their applications.

EmAmigo framework for developing behavior-based control systems of inspection robots

The paper deals with the implementation of the behavior-based control and learning framework for autonomous inspection robots. The presented control architecture is designed to be used in the mobile robot (Amigo) for the visual inspection of ventilation ducts. In this paper, various problems are discussed including brief description of hardware components (PC-104 modules), low-level hard real-time operating system (RTAI), high-level manual and autonomous mode control interface (Linux, KDE). The main aim of this paper is to present the framework for rapid control prototyping in the case of the inspection robot.