[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Next Issue
Volume 84, MEST 2024
Previous Issue
Volume 82, ECSA-11
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
engproc-logo

Journal Browser

Journal Browser

Eng. Proc., 2025, CITIIC 2023

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Number of Papers: 11
Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Other

6 pages, 355 KiB  
Editorial
Preface: III International Congress: Technology and Innovation in Engineering and Computing
by Luis Olivera-Montenegro
Eng. Proc. 2025, 83(1), 5; https://doi.org/10.3390/engproc2025083005 - 7 Jan 2025
Viewed by 313
Abstract
The III International Congress: Technology and Innovation in Engineering and Computing, organized by Faculty of Engineering, St [...] Full article
Show Figures

Figure 1

Figure 1
<p>Logo of USIL.</p>
Full article ">

Other

Jump to: Editorial

10 pages, 7549 KiB  
Proceeding Paper
Effect of the Process Parameters on the Mechanical Properties of 3D-Printed Specimens Fabricated by Material Extrusion 3D Printing
by Andoni Molina and Julio Acosta-Sullcahuamán
Eng. Proc. 2025, 83(1), 1; https://doi.org/10.3390/engproc2025083001 - 6 Jan 2025
Viewed by 218
Abstract
This work aims to study the influences of nozzle temperature, layer thickness and raster angles on the mechanical properties of acrylonitrile butadiene styrene (ABS) and polylactic acid (PLA) specimens fabricated by material extrusion 3D printing. Tensile tests were carried out in order to [...] Read more.
This work aims to study the influences of nozzle temperature, layer thickness and raster angles on the mechanical properties of acrylonitrile butadiene styrene (ABS) and polylactic acid (PLA) specimens fabricated by material extrusion 3D printing. Tensile tests were carried out in order to evaluate the mechanical properties of ABS and PLA specimens. The results showed that tensile strength decreased at a higher nozzle temperature for ABS, while an increase followed by a decrease in tensile strength occurred for PLA, with the maximum value obtained at 250 °C. Scanning electronic microscopy was used to analyze the surface fracture after tensile tests of specimens fabricated with different nozzle temperatures. Moreover, the highest tensile strength values for both ABS and PLA were achieved with a raster angle of [0°], the same direction as the applied tensile load. Additionally, a higher tensile strength was obtained for both ABS and PLA at a lower layer thickness. Based on these results, the process parameters used to manufacture a 3D object influence its mechanical properties. Full article
Show Figures

Figure 1

Figure 1
<p>Schematic representation of a 3D-printed tensile specimen and its main process parameters.</p>
Full article ">Figure 2
<p>Tensile strength vs. nozzle temperature for ABS and PLA specimens.</p>
Full article ">Figure 3
<p>SEM images of the fracture surface of ABS tensile specimens at (<b>a</b>) 200 °C and (<b>b</b>) 270 °C.</p>
Full article ">Figure 4
<p>SEM images of the fracture surface of PLA tensile specimens at (<b>a</b>) 200 °C, (<b>b</b>) 230 °C, (<b>c</b>) 250 °C and (<b>d</b>) 270 °C.</p>
Full article ">Figure 4 Cont.
<p>SEM images of the fracture surface of PLA tensile specimens at (<b>a</b>) 200 °C, (<b>b</b>) 230 °C, (<b>c</b>) 250 °C and (<b>d</b>) 270 °C.</p>
Full article ">Figure 5
<p>Tensile strength vs. layer thickness for ABS and PLA specimens.</p>
Full article ">Figure 6
<p>Tensile strength vs. raster angle for ABS and PLA specimens.</p>
Full article ">
9 pages, 3011 KiB  
Proceeding Paper
Design, Manufacturing and Mechanical Evaluation of a 3D Printed Customized Wrist-Hand Orthosis for the Treatment of De Quervain Tenosynovitis
by Sofia Franco, Mauricio Ramos, Renzo Cordova, Emilio Ochoa, Gianella Ccama and Andoni Molina
Eng. Proc. 2025, 83(1), 2; https://doi.org/10.3390/engproc2025083002 - 6 Jan 2025
Viewed by 244
Abstract
De Quervain’s tenosynovitis is a pathology that affects the tendons of the thumb and generates pain and inflammation, being common in people between 18 and 30 years old who perform repetitive movements. Despite the innovation of 3D printing in orthotics, customization is lacking. [...] Read more.
De Quervain’s tenosynovitis is a pathology that affects the tendons of the thumb and generates pain and inflammation, being common in people between 18 and 30 years old who perform repetitive movements. Despite the innovation of 3D printing in orthotics, customization is lacking. Therefore, this works aims to develop a 3D printed customized wrist-hand orthosis (WHO) for the treatment of De Quervain tenosynovitis. The WHO includes three main parts, which would be two faces that cover the front and back of the hand and the locks to ensure the coupling of both faces. Prior to 3D printing, feedstock filament characterization tests were carried out, and tensile strength, melt flow index, degradation, and melting temperature were obtained. 3D printing of the WHO was achieved in a short time and with an adequate fit. Subsequently, mechanical tests were carried out to evaluate the maximum force of the WHO in different positions. Full article
Show Figures

Figure 1

Figure 1
<p>Solution concept.</p>
Full article ">Figure 2
<p>Area involved in immobilization [<a href="#B12-engproc-83-00002" class="html-bibr">12</a>]. A: Distal metacarpal area, B: Base of the thumb, C: Central Dorsal Area, D: Wrist Area, E: Distal palmar area.</p>
Full article ">Figure 3
<p>Autodesk Fusion 360: Selection of side of application of force (blue arrow).</p>
Full article ">Figure 4
<p>Manufacturing process of WHO.</p>
Full article ">Figure 5
<p>Mechanical test of WHO.</p>
Full article ">Figure 6
<p>Wrist movements, modified of [<a href="#B16-engproc-83-00002" class="html-bibr">16</a>]. (<b>A</b>) Flexion, (<b>B</b>) Extension, (<b>C</b>) Ulnar deviation and (<b>D</b>) Radial deviation.</p>
Full article ">Figure 7
<p>FTIR results.</p>
Full article ">Figure 8
<p>Manufacturing results: (<b>a</b>) Orthosis printed in 90° degrees. (<b>b</b>) Orthosis printed in 45° to the left. (<b>c</b>) Orthosis printed in 75° to the front.</p>
Full article ">
9 pages, 2119 KiB  
Proceeding Paper
Additive Manufacturing of Reinforced Thermoplastic Nanoclay Particle Composites by Fused Filament Fabrication
by Andoni R. Molina and Julio Acosta-Sullcahuamán
Eng. Proc. 2025, 83(1), 3; https://doi.org/10.3390/engproc2025083003 - 7 Jan 2025
Viewed by 235
Abstract
In this study, reinforced thermoplastic nanoclay particle composites were prepared and used as filaments for additive manufacturing of specimens by using fused filament fabrication (FFF). Acrylonitrile butadiene styrene (ABS) and polylactic acid (PLA) were used as thermoplastic polymer matrices. The particle reinforced composite [...] Read more.
In this study, reinforced thermoplastic nanoclay particle composites were prepared and used as filaments for additive manufacturing of specimens by using fused filament fabrication (FFF). Acrylonitrile butadiene styrene (ABS) and polylactic acid (PLA) were used as thermoplastic polymer matrices. The particle reinforced composite feedstock filaments were fabricated from ABS and PLA pellets with different contents of nanoclay particles in a twin-screw extruder. Tensile and impact tests were carried out to evaluate the mechanical properties of the composite specimens fabricated by FFF. The mechanical test results showed an increase in the tensile strength of ABS matrix composites, but a decrease in the impact strength. For the case of PLA matrix composites, the tensile strength decreased when introducing the nanoclay particles and only with 3% of nanoclay particles was an increase of impact strength observed. Successful additive manufacturing of the particle-reinforced composite was achieved. Full article
Show Figures

Figure 1

Figure 1
<p>Representation of mixing and extrusion process during the fabrication of composite filaments.</p>
Full article ">Figure 2
<p>Tensile specimens of (<b>a</b>) ABS composites and (<b>b</b>) PLA composites.</p>
Full article ">Figure 3
<p>TGA results of (<b>a</b>) ABS and (<b>b</b>) PLA pellets.</p>
Full article ">Figure 3 Cont.
<p>TGA results of (<b>a</b>) ABS and (<b>b</b>) PLA pellets.</p>
Full article ">Figure 4
<p>MFI results of nanoclay reinforced ABS and PLA composites.</p>
Full article ">Figure 5
<p>Tensile strength of nanoclay-reinforced ABS and PLA composites.</p>
Full article ">Figure 6
<p>Impact strength of nanoclay reinforced ABS and PLA composites.</p>
Full article ">
9 pages, 2397 KiB  
Proceeding Paper
The Evaluation of the Seismic Performance of Unsymmetric-Plan Tall Buildings Using Modal Spectral Time History and Multi-Mode Pushover Analysis
by Luis A. Flores and Rick M. Delgadillo
Eng. Proc. 2025, 83(1), 6; https://doi.org/10.3390/engproc2025083006 - 8 Jan 2025
Viewed by 175
Abstract
In recent seismic events that occurred worldwide and in Peru, it has been observed that irregular structures in plan present greater structural damage compared to regular structures. Investigations carried out after seismic events indicate that irregular plan structures collapse due to erroneous structural [...] Read more.
In recent seismic events that occurred worldwide and in Peru, it has been observed that irregular structures in plan present greater structural damage compared to regular structures. Investigations carried out after seismic events indicate that irregular plan structures collapse due to erroneous structural conception and poor seismic analysis. Likewise, the Peruvian earthquake-resistant standard does not establish a permissible limit for the degree of irregularity under analysis, instead qualitatively assessing the structural irregularity. The objective of this article was to study the effect of plan irregularities using innovative methodologies on the structural response of tall 10-story reinforced concrete buildings. In this sense, seventeen (17) structural models are proposed that reflect different irregular configurations in plan: 06 structures Type L, 05 structures Type I, 05 structures Type I, and one regular building. These buildings are numerically modeled using ETABS software V.18.0 through modal analysis, Modal Spectral and Linear Time History (MSLTH), and Multi-Mode Pushover (MPA). For the MSLTH, seven (07) pairs of representative Peruvian earthquakes were analyzed. The results of the modal analysis evaluated in the first two vibration modes demonstrated that Type L irregular structures change their behavior from translational to torsional when the structures present an irregularity greater than 57%. Type I and O structures present translational behavior. Furthermore, the results of the Modal Spectral and MSLTH analysis demonstrate that Type L structures present greater displacements and drifts in both directions. The shear force and the overturning moment for Types L, I, and O decrease as the irregularity in plan increases. Finally, the results of the MPA for irregular Type L structures demonstrated that the lateral stiffness of the structures decreases as the irregularity in plan is critical, increasing the possibility of the formation of plastic mechanisms in the structural elements. Full article
Show Figures

Figure 1

Figure 1
<p>Structural models analyzed: (<b>a</b>) Base structural model (Pattern Model); (<b>b</b>) Type L structural models.</p>
Full article ">Figure 2
<p>Structural models analyzed: (<b>a</b>) Type I structural models; (<b>b</b>) Type O structural models.</p>
Full article ">Figure 3
<p>Pseudo acceleration spectrum.</p>
Full article ">Figure 4
<p>Lateral displacement: (<b>a</b>) Lateral displacement in X direction; (<b>b</b>) Lateral displacement in Y direction.</p>
Full article ">Figure 5
<p>Story drift: (<b>a</b>) Story drift in X direction; (<b>b</b>) Story drift in Y direction.</p>
Full article ">Figure 6
<p>Base shear: (<b>a</b>) Base shear in X direction; (<b>b</b>) Base shear in Y direction.</p>
Full article ">Figure 7
<p>Maximum overturning moment: (<b>a</b>) Maximum overturning moment in X direction; (<b>b</b>) Maximum overturning moment in Y direction.</p>
Full article ">Figure 8
<p>(<b>a</b>) Bilinear representation of structural models (<b>b</b>) L-type structure ductility.</p>
Full article ">
6 pages, 362 KiB  
Proceeding Paper
A Survey of Process Mining for Customer Management
by Javier Dioses and Leyde Cordova
Eng. Proc. 2025, 83(1), 7; https://doi.org/10.3390/engproc2025083007 - 8 Jan 2025
Viewed by 204
Abstract
Currently, organizations are experiencing rapid growth in the digitization of their processes, which generates a high availability of data and metadata in information systems generated by the activities of operations and support areas. This is important for business because it allows them to [...] Read more.
Currently, organizations are experiencing rapid growth in the digitization of their processes, which generates a high availability of data and metadata in information systems generated by the activities of operations and support areas. This is important for business because it allows them to analyze and understand the customer journey to provide a better experience to consumers and generate value in organizations. One way to analyze the customer journey is to use process discovery to obtain an optimal process model. There are several process discovery algorithms that allow for analyzing different business process models. In this paper, we focus on the customer experience because we have found that this is a trend in business that has rarely been addressed using process discovery by means of event logs. Thus, in this study, we conduct a literature review of primary articles about the use of process discovery algorithms using event logs from information systems to provide a better understanding on this topic. As a result, we have found that Heuristic Miner, Alpha Miner, and Inductive Miner are the most used algorithms for customer process discovery. Finally, we explain our findings about process discovery in the customer experience and why this is an emerging topic. Full article
Show Figures

Figure 1

Figure 1
<p>Evolution of articles studied in the present work for each year, selected in the search string.</p>
Full article ">
8 pages, 1424 KiB  
Proceeding Paper
A Convolutional Neural Network for Early Supraventricular Arrhythmia Identification
by Emilio J. Ochoa and Luis C. Revilla
Eng. Proc. 2025, 83(1), 8; https://doi.org/10.3390/engproc2025083008 - 8 Jan 2025
Viewed by 162
Abstract
Supraventricular arrhythmias (SVAs), including the often-asymptomatic supraventricular extrasystole (SVE), pose significant challenges in early detection and precise diagnosis. These challenges are of paramount importance, as recurrent SVEs may elevate the risk of developing severe SVAs, potentially resulting in cardiac weakening and subsequent heart [...] Read more.
Supraventricular arrhythmias (SVAs), including the often-asymptomatic supraventricular extrasystole (SVE), pose significant challenges in early detection and precise diagnosis. These challenges are of paramount importance, as recurrent SVEs may elevate the risk of developing severe SVAs, potentially resulting in cardiac weakening and subsequent heart failure. In the study conducted, an innovative approach was introduced that combined a convolutional neural network (CNN) architecture to enable the early identification and characterization of SVEs within electrocardiogram (ECG) signals. The analysis leveraged a dataset comprising 78 half-hour recordings from the highly regarded MIT-BIH Arrhythmia Database, which included annotation headers serving as labels for each recording. Signals were down-sampled by a factor of 2 and split into windows of 512 samples, with 12,288 observations for training. Following the methodology, classic signal preprocessing techniques (filtering and data normalization) were used. The proposed model was based on the UNET 1D model. A binary cross-entropy loss function, Adam optimizer, and a batch size of 128 were obtained after a hyperparameter tuning. As a training-validation methodology, a 50-fold cross-validation technique was used. The approach demonstrated a Dice coefficient of 79.01%, a precision of 80.96%, and a recall rate of 86.60% in detecting SVE events. These findings were corroborated through meticulous comparison with the annotations provided by the MIT-BIH database. The results underscore the immense potential of CNN and deep learning techniques in the early detection of supraventricular arrhythmias. This approach not only offers a valuable tool for healthcare professionals engaged in telemonitoring and early intervention strategies but also represents a significant contribution to the field of cardiac health monitoring. By facilitating efficient and precise identification of SVEs, our research sets the stage for improved patient outcomes and the prevention of severe SVAs, marking substantial advancements in this critical domain. Full article
Show Figures

Figure 1

Figure 1
<p>Architecture of the proposed convolutional neural network model.</p>
Full article ">Figure 2
<p>Project flowchart. It starts with the choice of databases, a preprocessing of the dataset, the preparation of the neural network, its evaluation, and, finally, its validation.</p>
Full article ">Figure 3
<p>Results of neural network segmentation for the detection of supraventricular extrasystole in an electrocardiogram signal. Interval detected.</p>
Full article ">Figure 4
<p>Results of neural network segmentation for the detection of supraventricular extrasystole in an electrocardiogram signal. ECG signal superposed.</p>
Full article ">Figure 5
<p>Probability level of recognition of an SVE (<b>left</b>) and its respective segmented signal in an ECG: red (training), green (validation), and brown (coincidence) (<b>right</b>).</p>
Full article ">
8 pages, 7391 KiB  
Proceeding Paper
Comparative Analysis of LiDAR Inertial Odometry Algorithms in Blueberry Crops
by Ricardo Huaman, Clayder Gonzalez and Sixto Prado
Eng. Proc. 2025, 83(1), 9; https://doi.org/10.3390/engproc2025083009 - 9 Jan 2025
Viewed by 223
Abstract
In recent years, LiDAR Odometry (LO) and LiDAR Inertial Odometry (LIO) algorithms for robot localization have considerably improved, with significant advancements demonstrated in various benchmarks. However, their performance in agricultural environments remains underexplored. This study addresses this gap by evaluating five state-of-the-art LO [...] Read more.
In recent years, LiDAR Odometry (LO) and LiDAR Inertial Odometry (LIO) algorithms for robot localization have considerably improved, with significant advancements demonstrated in various benchmarks. However, their performance in agricultural environments remains underexplored. This study addresses this gap by evaluating five state-of-the-art LO and LIO algorithms—LeGO-LOAM, DLO, DLIO, FAST-LIO2, and Point-LIO—in a blueberry farm setting. Using an Ouster OS1-32 LiDAR mounted on a four-wheeled mobile robot, the algorithms were evaluated using the translational error metric across four distinct sequences. DLIO showed the highest accuracy across all sequences, with a minimal error of 0.126 m over a 230 m path, while FAST-LIO2 achieved its lowest translational error of 0.606 m on a U-shaped path. LeGO-LOAM, however, struggled due to the environment’s lack of linear and planar features. The results underscore the effectiveness and potential limitations of these algorithms in agricultural environments, offering insights into future improvements and adaptations. Full article
Show Figures

Figure 1

Figure 1
<p>Designated paths for each sequence followed by the robot at the blueberry farm, where each letter represents a waypoint along the trajectories.</p>
Full article ">Figure 2
<p>Wheeled mobile robot at the blueberry farm. (<b>a</b>) The robot in its initial position within an inter-row space. (<b>b</b>) The robot transitioning between blocks of crops and the separation between these marked with a yellow measuring tape.</p>
Full article ">Figure 3
<p>Estimated trajectories by each algorithm during sequences AB and AC.</p>
Full article ">Figure 4
<p>Estimated trajectories by each algorithm during sequences AD and AF.</p>
Full article ">Figure 5
<p>Close-up views of the 3D maps generated using DLIO, with each label designating the corresponding sequence from the Blueberry Crop Dataset. The path taken to create these maps is shown in yellow. The point cloud color indicates the intensity of the point return.</p>
Full article ">
12 pages, 4916 KiB  
Proceeding Paper
Ecological Protection: Cell Phone Stand with Cable Winding Made of Polypropylene
by Deysi Vanessa Canchis Paredes, Jerson Córdova Salas and Ruben Felipe Vidal Endara
Eng. Proc. 2025, 83(1), 10; https://doi.org/10.3390/engproc2025083010 - 13 Jan 2025
Viewed by 140
Abstract
In an increasingly digitized environment, the deterioration of cell phone cables has led to a significant environmental impact due to the lack of adequate protection and care. This often results in cell phone charging cables being in poor condition. Cable damage can include [...] Read more.
In an increasingly digitized environment, the deterioration of cell phone cables has led to a significant environmental impact due to the lack of adequate protection and care. This often results in cell phone charging cables being in poor condition. Cable damage can include situations such as dirt accumulation or incorrect bending, leading to breakage. As a result, the objective was determined to design a prototype of a cell phone holder with internal biodegradable cable winding. Ulrich and Eppinger served as the methodological basis for the design, following phases including customer needs identification, setting objective values, product concept generation, concept selection, concept testing, and final specification filtering. A survey of 100 individuals provided valuable data for validating certain metrics. Additionally, two focus groups with 15 users were conducted, two experts were interviewed, and a 72 h usage test was carried out, all supported by the agile Scrum methodology and the Scamper technique, allowing for feedback and validation of the initial concept. The final prototype was modeled in 3D using the Lumion 11 program and physically constructed, ensuring functionality and adaptability of the cell phone and charger. In conclusion, a cell phone holder with a cable winder was designed, facilitating easy transport and prolonging the lifespan of any charger cable. Full article
Show Figures

Figure 1

Figure 1
<p>Empathy map of the customer who purchases the cell phone holder with cable winder.</p>
Full article ">Figure 2
<p>Survey question: Would you be willing to buy a cell phone and cable holder that you can take everywhere and that allows you to protect both the charger cable and your smartphone while it is plugged in and charging the battery?</p>
Full article ">Figure 3
<p>Survey question: How important is it to protect your mobile device and your smartphone’s charger cable?</p>
Full article ">Figure 4
<p>Survey question: What features do you think a wall cell phone holder with cable winder should have?</p>
Full article ">Figure 5
<p>Functional grouping diagram of the cell phone holder with cable winder.</p>
Full article ">Figure 6
<p>DOP of the cell phone holder with cable winder.</p>
Full article ">Figure 7
<p>Focus photo group 1.</p>
Full article ">Figure 8
<p>(<b>a</b>) Expert 1 testing prototype; (<b>b</b>) Expert 2 testing prototype.</p>
Full article ">Figure 9
<p>(<b>a</b>) Photo of the cable winding process; (<b>b</b>) front photo of the prototype.</p>
Full article ">Figure 10
<p>Use-test field diary.</p>
Full article ">Figure 11
<p>Front view of the cell phone holder with finished cable winder.</p>
Full article ">Figure 12
<p>Winder knob base.</p>
Full article ">Figure 13
<p>Plan of the views of the cell phone holder.</p>
Full article ">Figure 14
<p>Winding knob plan.</p>
Full article ">
9 pages, 1825 KiB  
Proceeding Paper
NevusCheck: A Dysplastic Nevi Detection Model Using Convolutional Neural Networks
by Andreluis Ingaroca-Torres, Lucía Heredia-Moscoso and Alvaro Aures-García
Eng. Proc. 2025, 83(1), 11; https://doi.org/10.3390/engproc2025083011 - 13 Jan 2025
Viewed by 125
Abstract
Dysplastic nevi are skin lesions that have distinctive clinical features and are considered risk markers for the development of melanoma, the deadliest type of skin cancer. A specific deep learning technique to identify diseases is convolutional neural networks (CNNs) because of their great [...] Read more.
Dysplastic nevi are skin lesions that have distinctive clinical features and are considered risk markers for the development of melanoma, the deadliest type of skin cancer. A specific deep learning technique to identify diseases is convolutional neural networks (CNNs) because of their great capacity to extract features and classify objects. Therefore, the research aims to develop a model to diagnose dysplastic nevi using a deep learning network whose classification is based on the pre-trained architecture EfficientNet-B7, which was selected for its high classification accuracy and low computational complexity. As for the results obtained, an accuracy of 78.33% was achieved in the classification model. Also, the degree of similarity between the detection by a dermatology expert and the proposed model reached an accuracy of 79.69%. Full article
Show Figures

Figure 1

Figure 1
<p>Flowchart of the proposed model for the detection of dysplastic nevi.</p>
Full article ">Figure 2
<p>Preprocessing techniques applied to a dysplastic nevus image.</p>
Full article ">Figure 3
<p>Flowchart of the UNet model for image segmentation.</p>
Full article ">Figure 4
<p>Distribution of the samples of 50 people.</p>
Full article ">Figure 5
<p>Comparison of dysplastic nevi detections by a dermatology expert and the proposed model.</p>
Full article ">
8 pages, 6110 KiB  
Proceeding Paper
Remote Control Device for the Detection and Correction of Errors in the FDM 3D Printing Process in Real Time
by Henry Requena, Kelvin Pozuelo, Carlos Díaz and Jean Coll
Eng. Proc. 2025, 83(1), 12; https://doi.org/10.3390/engproc2025083012 - 14 Jan 2025
Viewed by 24
Abstract
This project focuses on developing a remote control device for the real-time detection and correction of errors in fused deposition modeling (FDM) 3D printing. It utilizes a Raspberry Pi computer and a webcam to capture images while a neural network trained with a [...] Read more.
This project focuses on developing a remote control device for the real-time detection and correction of errors in fused deposition modeling (FDM) 3D printing. It utilizes a Raspberry Pi computer and a webcam to capture images while a neural network trained with a dataset generated by the research team identifies errors such as warping, stringing, and spaghetti. Information is efficiently transmitted via MQTT, with instant notifications through Telegram and a user interface. The methodology spans from training the neural network to integrated control strategies with the remote device. Evaluation highlights high precision using confusion matrices and IoU, promising substantial improvements in industrial and critical 3D printing environments. Full article
Show Figures

Figure 1

Figure 1
<p>(<b>a</b>) Ender 3 3D printer machine; (<b>b</b>) Raspberry Pi 4 model B 4 GB RAM; (<b>c</b>) manually focused USB camera.</p>
Full article ">Figure 2
<p>Images of 3D printing errors: (<b>a</b>) warping; (<b>b</b>) spaghetti; (<b>c</b>) stringing.</p>
Full article ">Figure 3
<p>Diagram of 3D printer all time serial communications.</p>
Full article ">Figure 4
<p>MQTT publish/subscribe architecture.</p>
Full article ">Figure 5
<p>YOLOv5 pretrained models performance.</p>
Full article ">Figure 6
<p>Images capturing errors generated for training an object detection model.</p>
Full article ">Figure 7
<p>Image labeling with LabelImg.</p>
Full article ">Figure 8
<p>User interface for 3D printer control.</p>
Full article ">Figure 9
<p>Trained model confusion matrix.</p>
Full article ">Figure 10
<p>Intersection over union.</p>
Full article ">Figure 11
<p>Intersection over union analysis: (<b>a</b>) warping; (<b>b</b>) stringing; (<b>c</b>) spaghetti.</p>
Full article ">
Previous Issue
Back to TopTop