Are Today’s SHM Procedures Suitable for Tomorrow’s BIGDATA?

Abstract

Large SHM datasets often result from special applications such as long-term monitoring, dense sensor arrays, or high sampling rates. Through the development of novel sensing techniques as well as advances in sensing devices and data acquisition technology, it is expected that such large volumes of measurement data become commonplace. In anticipation of datasets magnitudes larger than today's, it is important to evaluate current SHM processing methods at BIGDATA standards and identify potential limitations within computational procedures. This paper will focus on the processing of large SHM datasets and the computational sensitivity of common SHM procedures. Processing concerns encompass efficiency and scalability of SHM software, particularly the computational sensitivity of common system identification and damage detection algorithms with respect to a large amount of sensors and samples. IntroductionThe data acquisition process plays a key role in the monitoring of structural systems. Over the years, sensing networks have evolved from basic to complex. Today, structural response quantities are measured with high resolution in time and space by means of wired and wireless contact sensors as well as noncontact digital camera lenses. In order to infer about structural health condition, the measured signals are processed through various SHM algorithms (system identification, model calibration, and damage detection). Therefore, along with improvement in sensing technology, it is critical to evaluate the performance of SHM algorithms to study their scalability potential and overcome possible limitations in processing large SHM datasets. Toward this goal, this paper investigates performance of a subset of the current SHM procedures with growth of network size and data acquisition interval. This investigation is conducted in two parts: the preprocessing of measured data as the first step in any SHM procedure, and the computational cost of certain system identification and damage detection algorithms. Although it is expected that BIGDATA storage requirements will be far greater than limits of local hard disks and RAM, this aspect of the problem is outside of the scope of this paper. Exactly How Big Is "BIGDATA"?Today, a dataset earns the title "large" from the sizes of its dimensions and storage space. SHM datasets are typically multivariate times series with two dimensions: number of sensors and number of time samples. However, the mere storage requirements, say in megabytes, of a dataset is not enough to constitute the title "BIGDATA". Inherently, BIGDATA requires "BIGPROCESSING", a subsequent analysis of BIGDATA, of which computational complexity varies among SHM applications and techniques.

Direct State-Space Models for Time-Varying Sensor Networks

“…For example, BIGDATA refers to a very large data matrix constructed through the use of an equivalently large number of sensors during data acquisition network. In such cases, it is not possible, nor in many cases is it necessary, to process all of this BIGDATA simultaneously, if at all; even elementary operations such as uploading all measured data for processing could require significant computational efforts [13]. Offline DSN datasets provide a useful technique to is to extract an information-packed subset from the BIGDATA population.…”

“…After data acquisition, a very large quantity of data is available, which can be organized as a BIGDATA matrix. Due to computational and storage restrictions, it is difficult or impossible to analyze this data matrix as a whole [13]; however, for many SHM applications, such an analysis is not necessarily required. In other words, it is possible to extract a considerable amount of structural health information without examining every entry of the BIGDATA matrix.…”

Sensitivity Metrics for Maximum Likelihood System Identification

“…The quantification of uncertainty as a result of parameter estimation for a broad class of statistical estimators would prove to be a useful metric for evaluation or selection of identification techniques. The adequacy of an estimator is especially a concern in the rapidly evolving field of SHM; as collected data reach larger sizes and new formats, such as BIGDATA (Matarazzo et al 2015) or mobile sensing (Matarazzo and Pakzad 2015b), trusted estimation techniques with measureable precision become increasingly valuable.…”

Machine learning based novelty detection using modal analysis

“…While ideally the change in the structure can be detected by inspecting features such as natural frequencies, the environmental or operational variations often pollute the baseline and prevent an accurate assessment of the change. Over the last few years, with the advancements in affordable sensor technologies, SHM entered the era of big data (Matarazzo, Shahidi, Chang, & Pakzad, 2015;Liang et al, 2016;Wang et al, 2018). As a result of this, machine learning algorithms started to gain traction as a promising damage detection tool for explaining and modeling the relationship between structural responses and integrity under temporally changing conditions while harnessing the power of big data (Farrar & Worden, 2012;Lin, Pan, Wang, & Li, 2018;Worden & Manson, 2006).…”