Trigger Realignment by Networking Synchronized Embedded Hardware

Lamonaca, Francesco; Grimaldi, D.

doi:10.1109/tim.2012.2218058

Cited by 18 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[38], while hardware and software systems are implemented as described in Ref. [46]. The experimental tests were conducted on a set of concrete cubic specimens with dimension 15 x 15 x 15 cm 3 without any steel reinforcement (a full description of specimen preparation is also provided in Refs.…”

Section: Methodsmentioning

confidence: 99%

Automatic Crack Classification by Exploiting Statistical Event Descriptors for Deep Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven structural health monitoring (SHM) systems is gaining in popularity. This is due to the large availability of big data from low-cost sensors with communication capabilities and advanced modeling tools such as deep learning. A promising method suitable for smart SHM is the analysis of acoustic emissions (AEs), i.e., ultrasonic waves generated by internal ruptures of the concrete when it is stressed. The advantage in respect to traditional ultrasonic measurement methods is the absence of the emitter and the suitability to implement continuous monitoring. The main purpose of this paper is to combine deep neural networks with bidirectional long short term memory and advanced statistical analysis involving instantaneous frequency and spectral kurtosis to develop an accurate classification tool for tensile, shear and mixed modes originated from AE events (cracks). We investigated effective event descriptors to capture the unique characteristics from the different types of modes. Tests on experimental results confirm that this method achieves promising classification among different crack events and can impact on the design of the future of SHM technologies. This approach is effective to classify incipient damages with 92% of accuracy, which is advantageous to plan maintenance.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Crack Classification by Exploiting Statistical Event Descriptors for Deep Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The scene is then fully captured in the same way as for a photo, but the distance measurement is taken independently on each pixel, thus enabling 3D reconstruction of the measured object or scene. In this context the synchronization among the signals triggering the equipment hardware components is key factor [48]- [49]. It should be remembered, however, that infrared light does not contain any of the colours visible to our eye, so the image that the vision sensors detect, will only be black/white.…”

Section: Different Generations Of Automatic Milking Systemsmentioning

confidence: 99%

Comparative performance analysis between two different generations of an automatic milking system

Verde,

Matera,

Bonavolonta

et al. 2023

Acta IMEKO

View full text Add to dashboard Cite

The adoption of Automatic Milking Systems (AMS) in Europe and Italy has been increasing gradually in recent years, driven by the advantages they offer over traditional milking methods. AMS reduces the need for manual labor, increases milk production, standardizes teat cleaning and disinfection, and promotes animal welfare. The adoption of milking robots also allows for continuous monitoring of milk parameters, animal health status, and production performance. In a recent study, the authors analyzed the improvements achieved by a buffalo farm in Southern Italy that switched from an older model (Classic ) to a newer generation model (VMS 300) of milking robot, showing an increase in production quantity and quality.

show abstract

“…Owing to the heterogeneity of the concrete material and the imperfections of the sample (bubbles, defects) the comparison of the effectiveness with which the damage index is evaluated by using the two acquisition systems must be performed by placing the transducers of the two acquisition systems in the same place at the same time [28]. Since this approach is not possible in practice, the data are acquired by using the FAT and the case of the traditional AS is evaluated by discarding the data obtained when the ChX selected as input does not detect the trigger.…”

Section: Experimental Set-upmentioning

confidence: 99%

Improved Accuracy of Damage Index Evaluation in Concrete Structures by Simultaneous Hardware Triggering

Lamonaca¹,

Carrozzini²,

Grimaldi³

et al. 2014

Metrology and Measurement Systems

Self Cite

View full text Add to dashboard Cite

Non-invasive damage monitoring of concrete structures by means of Acoustic Emission (AE) requires multitransducers, multi-channel acquisition, high sampling frequency and long observation time. Owing to its propagation in concrete, the signal from AE reduces its amplitude during the propagation, and, consequently, some events can be lost due to lower signal intensity than the trigger level set on one sensor only. The innovative proposal discussed in the paper consists in the introduction of a Flat Amplifier and Trigger generator block (FAT) in order to generate a logical trigger when the AE is detected by any transducer. Experimental tests confirm the effectiveness of the FAT to acquire all the AE events and to increase the evaluation accuracy of damage indexes.

show abstract

Trigger Realignment by Networking Synchronized Embedded Hardware

Cited by 18 publications

References 19 publications

Automatic Crack Classification by Exploiting Statistical Event Descriptors for Deep Learning

Automatic Crack Classification by Exploiting Statistical Event Descriptors for Deep Learning

Comparative performance analysis between two different generations of an automatic milking system

Improved Accuracy of Damage Index Evaluation in Concrete Structures by Simultaneous Hardware Triggering

Contact Info

Product

Resources

About