The latest digital revolution involves the rise of smart devices composed of sensor hardware and artificial intelligence (AI) software for performing intelligent tasks. Smart sensors have become ubiquitous in our lives with varied applications ranging from voice-enabled home devices (Google Home, Alexa, etc.) to the Industrial Internet of Things (IIoT). This revolution has been fueled by 1) miniaturization of sensing hardware, 2) easy access to cloud and high-performance computing, 3) development of big data storage and analytics technologies, and 4) the latest breakthroughs in machine learning (ML) and AI technologies. The emergence of AI since 2012 and its major breakthroughs can be attributed to the research and development (R&D) in deep learning, a subfield of ML that uses biologically inspired neural networks to perform learning tasks. [1] The performance of conventional ML algorithms depends on the individual selection of specific features, while deep neural networks (DNN) automatically generate features as part of the learning process. Deep learningbased AI technologies are increasingly showing performance
Purpose
One of the major concerns of the constrained-surface stereolithography (SLA) process is that the built-up part may break because of the force resulting from the pulling-up process. This resultant force may become significant if the interface mechanism between the two contact surfaces (i.e. newly cured layer and the bottom of the resin vat) produces a strong bonding between them. The purpose of this paper is to characterize the separation process between the cured part and the resin vat by adopting an appropriate and simple mechanics-based model that can be used to probe the pulling-up process.
Design/methodology/approach
In this paper, the time-histories of the pulling-up forces are measured using FlexiForce® force sensors. The experimental data are analyzed and used to estimate the constitutive parameters of the separation mechanism. Here, the separation mechanism is modeled based on the concept of cohesive zone model (CZM) that is well-studied in the field of fracture mechanics. By using the experimentally measured pulling-up force, this paper proposes a very efficient inverse technique to estimate the constitutive parameters for the CZM. The constitutive laws for the CZM facilitate in relating the separation force at the interface between the cured part and the resin vat in terms of the pulling-up velocity. Unlike work proposed earlier, computationally expensive full-scale finite element runs are not essential in the current work while estimating the required parameters of the constitutive laws. Instead, mechanics-based computationally efficient surrogate model is proposed to readily estimate these constitutive parameters.
Findings
Two constitutive laws are compared on the basis of their predictions of the separation force profile. Excellent match is obtained between the measured and the predicted separation force profiles.
Originality/value
This paper selects a suitable mechanics-based model that can characterize the separation process and proposes a computationally efficient scheme to estimate the required constitutive parameters. The proposed scheme can be used to reliably predict the separation force for the constrained-surface SLA process, leading to improved productivity and reliability of the SLA processes in fabricating the built-up parts.
Emerging opportunities combining acoustic non-destructive evaluation, optical fiber sensing, and AI are discussed for infrastructure monitoring spanning electrical grid, oil and gas (CH4, H2, CO2) pipelines, oil and gas recovery, and civil (roads, bridges, water).
A vibration fiber sensor based on a fiber ring cavity laser and an interferometer based single-mode-multimode-single-mode (SMS) fiber structure is proposed and experimentally demonstrated. The SMS fiber sensor is positioned within the laser cavity, where the ring laser lasing wavelength can be swept to an optimized wavelength using a simple fiber loop design. To obtain a better signal-to-noise ratio, the ring laser lasing wavelength is tuned to the maximum gain region biasing point of the SMS transmission spectrum. A wide range of vibration frequencies from 10 Hz to 400 kHz are experimentally demonstrated. In addition, the proposed highly sensitive vibration sensor system was deployed in a field-test scenario for pipeline acoustic emission monitoring. An SMS fiber sensor is mounted on an 18” diameter pipeline, and vibrations were induced at different locations using a piezoelectric transducer. The proposed method was shown to be capable of real-time pipeline vibration monitoring.
This study presents a framework for detecting mechanical damage in pipelines, focusing on generating simulated data and sampling to emulate distributed acoustic sensing (DAS) system responses. The workflow transforms simulated ultrasonic guided wave (UGW) responses into DAS or quasi-DAS system responses to create a physically robust dataset for pipeline event classification, including welds, clips, and corrosion defects. This investigation examines the effects of sensing systems and noise on classification performance, emphasizing the importance of selecting the appropriate sensing system for a specific application. The framework shows the robustness of different sensor number deployments to experimentally relevant noise levels, demonstrating its applicability in real-world scenarios where noise is present. Overall, this study contributes to the development of a more reliable and effective method for detecting mechanical damage to pipelines by emphasizing the generation and utilization of simulated DAS system responses for pipeline classification efforts. The results on the effects of sensing systems and noise on classification performance further enhance the robustness and reliability of the framework.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.