Applications of Self-Organizing Maps in Structural Health Monitoring

Abstract

The Structural Health Monitoring process includes several steps like feature extraction and probabilistic decision making, which need some form of data fusion and information condensation. These take place after data acquisition and before being able to decide, if a monitored structure has faced damage. Although feature selection is an important step, the processing and suitable preparation of these data are significant, influencing the potential of decision making in various ways. With Self-Organizing Maps (SOM) a multi-purpose instrument for these tasks of pattern recognition and data interpretation is presented here. Self-Organizing Maps belong to the group of artificial neural networks and by using the special map character provide the opportunity of additional visualization. Especially when monitoring a structure over a long period of time, environmental changes often occur, which can mask the effects of damage on the dynamic behavior of the structures. As one potential application of SOM, the possibility of distinguishing between environmental changes and damage of the structure is shown. In this application a self-organizing network is trained with data of the undamaged structure and via calculation of the distance to the map a damage indicator is developed. Moreover, the distinction between different damage modes of piezoelectric sensors is presented using SOM as a tool of pattern recognition and visualization. This application uses data recorded from different damage modes extracted from one specimen of a piezoelectric element. The trained network can be compared with other piezoelectric elements mounted in a similar way to be able to detect possible sensor damage. This helps avoiding false alarms even under changing environmental conditions. Both applications have been successfully used to analyze experimental data on coupon level showing the applicability of the presented concepts.

Failure Assessment of Piezoelectric Actuators and Sensors for Increased Reliability of SHM Systems

“…As already shown in Eqs. (7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17), the model itself includes a bunch of parameters. Although most of them cannot be changed due to damage (e.g., nominal radius of the PWAS), these parameters will have some variations resulting from different batches, different bonding procedures, and so on.…”

“…The effort for this method is large, as the temperature dependence of all significant parameters has to be included within the model. Other efforts to compensate for varying environmental and operational conditions for signal-based techniques within wave-and vibration-based SHM systems use statistical damage classification [6,7] including, e.g., fuzzy classification [8], the use of neural networks [9] and self-organizing maps [10].…”

Model-based detection of sensor faults under changing temperature conditions

“…In equation (15), still x(v) has to be defined, see equation (7). While Giurgiutiu 4 uses the whole dynamic behaviour of the chosen structure, it is also possible to take as few as possible information about the structure into account, but choose more information about the adhesive layer.…”

“…6 The combination of k adh and k str leads to k str&adh according to equation (18). This way x(v) can be calculated by means of equation ( 7), which is necessary to finally calculate the admittance according to equation (15). For the sake of completeness, it should be mentioned that the used material constants (e.g.…”

“…A temperature dependency according to equation (34) is used for the above-mentioned parameters such as k i = E str (T ). E str (T ) is used in equation ( 19) and via x(v) (equations ( 7) and ( 18)) is also included in the calculation of the admittance in equation (15). This way the temperature dependency of the admittance is modelled.…”