Optimizing the placement of piezoelectric wafers on closed sections using a genetic algorithm - Towards application in structural health monitoring

Piezoelectric Materials and Sensors for Structural Health Monitoring: Fundamental Aspects, Current Status, and Future Perspectives

Structural health monitoring technology can assess the status and integrity of structures in real time by advanced sensors, evaluate the remaining life of structure, and make the maintenance decisions on the structures. Piezoelectric materials, which can yield electrical output in response to mechanical strain/stress, are at the heart of structural health monitoring. Here, we present an overview of the recent progress in piezoelectric materials and sensors for structural health monitoring. The article commences with a brief introduction of the fundamental physical science of piezoelectric effect. Emphases are placed on the piezoelectric materials engineered by various strategies and the applications of piezoelectric sensors for structural health monitoring. Finally, challenges along with opportunities for future research and development of high-performance piezoelectric materials and sensors for structural health monitoring are highlighted.

Particle Swarm Optimization Algorithm for Guided Waves Based Damage Localization Using Fiber Bragg Grating Sensors in Remote Configuration

Structural health monitoring (SHM) systems may allow a reduction in maintenance costs and extend the lifetime of the structure. As a result, they are of interest to the research community. Ideally, the SHM methods should be low cost, while being able to detect and localize small levels of damage reliably and accurately. The fiber Bragg grating (FBG) sensors are light in weight, insensitive to electric and magnetic fields, and can be embedded. The edge filtering configuration for transduction allows the use of FBG for guided wave (GW) sensing. This sensitivity may be further enhanced through their application in the remote bonded configuration. This paper provides a proof-of-concept for the use of remotely bonded FBG for damage localization. In order to improve the computational efficiency, a particle swarm optimization (PSO) based algorithm is developed. The PSO allows a significant improvement in the computation time which makes it better suited for real-time damage localization. The proposed objective function is based on the exponential elliptical approach. First, the suitability of the PSO for damage localization is shown. Then the performance of the chosen objective function is compared with the brute-force algorithm as well as other objective functions found in the literature. The methodology is employed on a simple aluminum plate. The results indicate that indeed the objective function along with the PSO is suitable for damage localization. Also as the objective function is developed taking into consideration the specific challenges with the use of FBG sensors, performs better than the other objective functions as well as the brute force algorithm.

Damage identification using wave damage interaction coefficients predicted by deep neural networks

The ever-increasing demand for efficiency and cost improvements in lightweight structures with guaranteed safety and reliability is leading to the application of a damage-tolerant design philosophy. Here, accurate knowledge of structural health is critical to avoid catastrophic failures. This knowledge can be obtained by using advanced structural health monitoring (SHM) systems. For thin-walled lightweight structures, methods utilizing guided waves generated by piezoelectric transducers are well suited. The interaction between the guided waves and potential damages can be described by so-called wave damage interaction coefficients (WDICs). These WDICs are unique for each damage and depend solely on its characteristics for a given structure. Therefore, the comparison of known WDICs with estimated ones allows drawing conclusions about the current structural state. In this paper, a novel damage identification method for plate-like structures based on a database of such WDICs is presented. Selected damages are simulated numerically with finite elements to generate WDIC patterns. However, these simulations are computationally highly demanding, thus only a very limited number of damage scenarios can be simulated. This study proposes an innovative technique to substantially enhance the resulting WDIC database by using deep neural networks (DNNs). These DNNs enable smart interpolations and allow not only predicting WDICs for previously unseen damages at low computational costs but also the discovery of knowledge about the complex relationship between damage features and WDIC patterns. A comparison to other machine learning algorithms clearly shows the superior performance of the utilized DNNs for interpolating complex WDIC patterns. The proposed damage identification method is verified using advanced time-domain simulations of a large aluminum plate. A statistical analysis of correct identification rates in a common three-sensor setting is employed for assessing the general performance. It is demonstrated that carefully identified DNNs enable to accurately replicate and interpolate complex WDIC patterns. Furthermore, it is shown that these predicted WDICs allow identifying damage characteristics with high confidence.