EMEA 2021 Student Forum: TinyML meets vibration-based Structural Health Monitoring: solving a…



EMEA 2021 Student Forum
TinyML meets vibration-based Structural Health Monitoring: solving a binary classification problem at the edge
Federica ZONZINI, PhD Student, University of Bologna, Italy

Structural Health Monitoring (SHM) is a trending discipline aiming at assessing the integrity condition of structures throughout their life cycle and in their normal operations. Hence, low-latency, long-term and real-time functionalities are three pillar design criteria to be leveraged while designing a resilient and effective monitoring system.

To this end, the Tiny Machine Learning (TinyML) paradigm has very recently pioneered outstanding solutions capable to optimize both the time and the dimension of the data to be processed and shared among the SHM network. TinyML could indeed bring a radical shift of perspective, moving from cloud-based data analytics, which is usually performed on remote servers in a time and energy consuming manner, to sensor-near data inference, empowered to smart sensors in charge of processing information in a streaming fashion.

Within this scenario, damage diagnosis and prognosis are the two main tasks in which TinyML founds its natural application. Accordingly, the contribution of this work is to present the practical embodiment of TinyML architectures on resource-constrained devices, devoted to the health assessment of structures in dynamic regime. The latter comprise all those application domains which can be thoroughly described by frequency-related quantities, which are conventionally extracted by means of standard spectral analysis techniques.
More in detail, the structural evaluation process was tackled as a binary classification problem. Such an approach yielded to the design of two different neural networks, which require natural frequencies of vibration as inputs and provide the corresponding damage status (i.e. healthy/unhealthy structure) as output. The neural network topology was taken from a standard feedforward Autoassociative Neural Network (ANN). However, due to the high dependency of these frequency parameters from environmental and operational factors (EOF), the neural network models were corrected by including a set of structurally sensitive EOF data (e.g. temperature) as additional inputs to the model. Differently from conventional implementations, the primary aim in pursuing this strategy is to make the network self-adaptative in regressing the EOF-to-frequency relationship without needing any standard regression and/or compensation technique to be performed aside.
The tested ANN models have been initially coded in the Python TensorFlow programming environment; then, their distilled versions, characterized by much a fewer number of hyperparamaters but similar classification performances, have been obtained after conversion to TensorFlow Lite. Finally, the sought models have been ported on the Arduino Nano 33 BLE Sense platform and validated with experimental data from the Z24 bridge use case, reaching an average accuracy and precision of 92% and 91%, respectively. The maximum model size was kept below 10 KB and the maximally measured execution time inferior to 1.5 s.

source

7 thoughts on “EMEA 2021 Student Forum: TinyML meets vibration-based Structural Health Monitoring: solving a…

  • August 20, 2021 at 6:30 am
    Permalink

    In line with my study, after a property foreclosure home is bought at a sale, it is common with the borrower in order to still have any remaining balance on the financial loan. There are many loan companies who try to have all expenses and liens cleared by the next buyer. Nevertheless, depending on specified programs, rules, and state legal guidelines there may be a few loans that aren’t easily sorted out through the transfer of lending products. Therefore, the duty still falls on the lender that has had his or her property in foreclosure process. Many thanks for sharing your thinking on this web site.

    Reply
  • August 25, 2021 at 11:51 am
    Permalink

    I want to point out my gratitude for your generosity giving support to those individuals that have the need for guidance on this subject matter. Your special commitment to getting the solution around had been unbelievably practical and have continually made associates much like me to achieve their targets. Your insightful useful information implies so much a person like me and much more to my colleagues. Thank you; from all of us.

    Reply
  • August 26, 2021 at 5:18 pm
    Permalink

    I have observed that over the course of building a relationship with real estate homeowners, you’ll be able to come to understand that, in every real estate deal, a commission rate is paid. Finally, FSBO sellers really don’t “save” the commission. Rather, they struggle to win the commission by means of doing the agent’s job. In doing this, they invest their money plus time to accomplish, as best they might, the responsibilities of an agent. Those assignments include displaying the home via marketing, delivering the home to prospective buyers, making a sense of buyer desperation in order to trigger an offer, organizing home inspections, handling qualification inspections with the financial institution, supervising maintenance, and assisting the closing of the deal.

    Reply
  • September 15, 2021 at 3:10 am
    Permalink

    One other issue is that if you are in a situation where you do not possess a cosigner then you may really want to try to make use of all of your school funding options. You can find many awards and other scholarship grants that will ensure that you get funds to help you with college expenses. Many thanks for the post.

    Reply
  • October 27, 2021 at 1:52 am
    Permalink

    Very good written article. It will be beneficial to everyone who usess it, including me. Keep up the good work – looking forward to more posts.

    Reply
  • October 29, 2021 at 12:35 pm
    Permalink

    Keep working ,splendid job!

    Reply
  • October 30, 2021 at 4:20 am
    Permalink

    Pretty great post. I simply stumbled upon your blog and wanted to mention that I have really loved browsing your blog posts. In any case I will be subscribing on your feed and I hope you write once more soon!

    Reply

Leave a Reply

Your email address will not be published.