Ziemowit Dworakowski

A structure's deflection measurement and monitoring system supported by a vision system

Abstract In this paper a vision-based method for measuring vertical deflection of large engineering structures under load is presented in example of crane working arm deflection measurements. The deflection is computed by means of a digital image correlation technique embedded in the vision-based system. The results of measurements performed on the vision system were compared with data obtained using a Leica Laser Tracker system. The comparison revealed proper functioning of the developed vision system in industrial conditions.

Data fusion for compensation of temperature variations in Lamb-wave based SHM systems

Temperature variations affect Lamb wave propagation and therefore in this way they can severely limit application of baseline signals in SHM systems. Various techniques are proposed in the paper to solve this problem. New method based on an interpretation of multiple signals acquired in distinct points of the structure is introduced and compared with other widely used approaches. Data fusion is used to merge a number of methods into one with a substantially increased efficiency.

Application of artificial neural networks for damage indices classification with the use of Lamb waves for the aerospace structures

Lamb waves (LW) are used for damage detection and health monitoring due to the long range propagation ability and sensitivity to structural integrity changes as well as their robustness in different applications. However, due to the dispersive character and multimode nature of LWs, analysis of the acquired ultrasonic signals is very complex. It becomes even more difficult when applied to a complex structure, for instance, an aircraft component with riveted joints and stringers characterized by difficult geometries. Therefore, numerous approaches to the evaluation of damage indices have been proposed in the literature. In this paper, comparison a number of damage indices applied to LWs testing in aircraft aluminum panels. The damage indices, known from the literature have been selected from the application point of view. Artificial neural network has been used for the classification of fatigue cracks and artificial damages induced in the specimens taken from a real aircraft structure. Article presents results of simulation, data analysis and data classification obtained using selected and dedicated neural network. The main aim of the presented research was to develop signal processing and signal classification methods for an aircraft health monitoring system. The article presents a part of the research carried out in the project named SYMOST.

Artificial neural network ensembles for fatigue damage detection in aircraft

Neural networks are commonly recognized tools for the classification of multidimensional data obtained in structural health monitoring (SHM) systems. Their configuration for a given scenario is, however, a challenging task, which limits the possibilities of their practical applications. In this article the authors propose using the neural network ensemble approach for the classification of SHM data generated by guided wave sensor networks. The overproduce and choose strategy is used for designing ensembles containing different types and sizes of neural networks. The proposed method allows for a significant increase of the state assessment reliability, which is illustrated by the results obtained from the practical industrial case of a full-scale aircraft test. The method is verified in the process of detecting fatigue cracks propagating in the aircraft load-carrying structure. The long-term experiments are performed in variable environmental conditions with a net of structure-embedded piezoelectric sensors.

Damage localization in plates with use of the procedure based on Modal Filtration

Modal filtering has numerous applications in the analysis of object dynamics. One possible use of this technique, recently presented in the literature, is damage detection. The main idea behind it, is to compare system characteristics filtered with modal filter for damaged and undamaged state. If a structural change appears in the system the filter does not work perfectly and its output significantly differs from one obtained for the healthy structure. Method is based on the modal parameter variation due to damage but does not require the modal analysis for every diagnosis. Another advantages are: computational simplicity and robustness for ambient temperature changes. The method was extended in 2008 with the possibility of damage localization. The idea here was based on the fact that local damage disturbs mode shapes locally. Instead of one modal filter, set of local modal filters were identified and used for further processing. Area of the structure connected with the filter with the worst performance is suspected of containing the damage. The method was already presented and positively verified but only for the beam-like structures. In this paper, application for plate-like structures is shown.

Selection of Suitable Method for Speed Recovery from Vibration Signal

Typically, if order analysis of vibration signal is expected, a speed sensor (phase marker) or an encoder are installed on the shaft. However, in some practical scenarios, the speed information recorded in parallel to the vibration signal acquisition is not available; yet, it is still required. In this case, one is forced to use a raw vibration signal to extract the information about so-called instantaneous phase or instantaneous frequency of a selected component, and—if required—scale to a selected shaft. In recent years, few different techniques for speed recovery have been proposed, each one with different assumptions and each implementing more or less complexed mathematical apparatus. The current paper proposes a guidance how to select a suitable method on the basis of the visual deduction about signal characteristics with the implication on selection of the easiest and most automatized method sufficient for analysed case.

Application of vision measurements for modal analysis of wires for the purpose of overhead transmission lines monitoring

Overhead transmission power lines are still one of the crucial elements of electro-energetic system. There are obvious advantages of using overhead transmission in the distribution of electricity. The amount of energy transported through a power line is determined by the distance between the wire and the ground or other objects placed beneath it (eg. trees). This distance is not fixed and depends on the overhang of the wire. This, in turn, is determined by many factors such as ambient temperature, humidity, precipitation, the value of current flowing through the wire. In order to optimize the wires electrical load, the monitoring of that overhang is required. One way to measure it is the non-contact measurement by vision system. It has the advantage, that using high-speed cameras respectively it also allows for vibration measurement and analysis of dynamic performance. That is very important while the wires are susceptible to the influence of wind, and the resulting vibrations interfere with the correct measurement of the overhang. The paper presents the results of vision measurements of the system vibrations and modal analysis carried out on their basis. The study was conducted on a specially made laboratory stand.

Ensemble ANN Classifier for Structural Health Monitoring

Type and structure of artificial neural network (ANN) have significant impact on its performance. Furthermore, networks of the same type and structure often perform differently due to the random distribution of initial weights. These issues cause the practical use of ANNs a challenging task. Some of the mentioned drawbacks can be eliminated using ensembles of ANNs. However, relevance of a single ensemble member might be different in different classification or regression tasks. In this paper we present an autonomous ensemble design method that includes selection of a subset of ANNs most suitable for solving of a specific task. The ensemble is able to change its structure by choosing the electors with respect to their training performance. The proposed method is tested in practical regression tasks in civil engineering structures monitoring.

Development of novel general equation for multistage epicyclic gearset with corrected teeth: fixed-speed approach

The paper illustrates a general equation in a new form, which allows calculating the characteristic frequencies of any kind of epicyclic gear sets with a ring, a sun, and planets. Moreover, presented equation takes into account corrected teeth (i.e. where the equality 2P+S=R is not fulfilled). This happens when gearboxes contain gears where corrected teeth procedure was adopted during designing stage. Presented solution can refine the configuration modules of the Condition Monitoring Systems (CMS) in such a way that allows to configure systems into larger groups than now available, i.e. multistage gear sets systems with epicyclic gears. Such CMS are capable of early mechanical faults detection, which prevents from costly critical repairs. For instance, fault detection of wind turbines is typically based on vibration and process signals analysis. Illustrated possible enhancement of configuration module is the basis for determining the energy bands in the spectra and envelope spectra in the process of identifying characteristic frequencies caused by gear defects.

Development of novel general equation for multistage epicyclic gearset with corrected teeth: non-constrained approach

A large number of commercial systems for condition monitoring of most common planetary gearboxes used in wind turbines and mining machinery have been developed for years. However nowadays, multistage constructions are encountered in industries. These are not necessarily planetary, but generally epicyclic. Current state of the art, according to the authors knowledge, does not give general equations for a case where multistage systems are considered, where some of the gears consist all moving parts. Hence, currently available CMS systems are not suitable for condition monitoring of these kinds of systems. The paper presents a new general equation, which allows calculating the characteristic frequencies of any kind of multistage gear sets, as a result of theoretical investigation. Illustrated solution does not assume a fixed speed of any element. Moreover, presented equation takes into account corrected teeth, making developed equations most general from all available in tribology science. Presented scientific development is currently implemented in a modern European CMS.