scholarly journals Image-based failure detection for material extrusion process using a convolutional neural network

2020 ◽  
Vol 111 (5-6) ◽  
pp. 1291-1302
Author(s):  
Hyungjung Kim ◽  
Hyunsu Lee ◽  
Ji-Soo Kim ◽  
Sung-Hoon Ahn
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Failure Detection ◽  
Extrusion Process ◽  
Shape Error ◽  
Material Extrusion ◽  
Recognition Of Objects ◽  
Deposition Processes ◽  
Printing Processes ◽  
Visual Geometry

Abstract The material extrusion (ME) process is one of the most widely used 3D printing processes, especially considering its use of inexpensive materials. However, the error known as the “spaghetti-shape error,” related to filament tangling, is a common problem associated with the ME process. Once occurring, this issue, which consumes both time and materials, requires a restart of the entire process. In order to prevent this, the user must constantly monitor the process. In this research, a failure detection method which uses a webcam and deep learning is developed for the ME process. The webcam captures images and then analyzes them by machine learning based on a convolutional neural network (CNN), showing outstanding performance in both image classification and the recognition of objects. Sample images were trained based on a modified Visual Geometry Group Network (VGGNet) model and the trained model was evaluated, resulting in 97% accuracy. The pre-trained model was tested on a 3D printer monitoring system for its ability to recognize the “spaghetti-shape-error” and was able to detect 96% of abnormal deposition processes. The proposed method can analyze the ME process in real time and informs the user or halts the process when abnormal printing is detected.

scholarly journals Implementasi Metode Convolutional Neural Network Menggunakan Arsitektur LeNet-5 untuk Pengenalan Doodle

2020 ◽  
Vol 1 (1) ◽  
pp. 45-56
Author(s):  
Muhammad Rafly Alwanda ◽  
Raden Putra Kurniawan Ramadhan ◽  
Derry Alamsyah
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Test Results ◽  
The Third ◽  
Recognition Of Objects ◽  
Handwritten Recognition

Recognition of objects to date has been widely applied in various fields, for example in handwritten recognition. This research utilizes the ability of CNN to use LeNet-5 architecture for the introduction of doodle types with 5 object images, namely clothes, pants, chairs, butterflies and bicycles. Each doodle object consists of 30 images with a total dataset of 150 images. The test results show that the first, second and fourth scenarios of bicycle objects are more recognized with an accuracy value of 93% - 98%, recall 86% - 93% and precision 81% - 93%, clothes objects are more recognized in the third scenario with an accuracy value of 94%, 86% recall, and 83% precision.

scholarly journals A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks

Algorithms ◽  
2018 ◽  
Vol 11 (10) ◽  
pp. 159 ◽  
Author(s):  
Yulin Zhao ◽  
Donghui Wang ◽  
Leiou Wang ◽  
Peng Liu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computational Complexity ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Computational Burden ◽  
Filtering Algorithm ◽  
Video Recognition ◽  
Conventional Algorithm ◽  
Visual Geometry

Convolutional neural networks have achieved remarkable improvements in image and video recognition but incur a heavy computational burden. To reduce the computational complexity of a convolutional neural network, this paper proposes an algorithm based on the Winograd minimal filtering algorithm and Strassen algorithm. Theoretical assessments of the proposed algorithm show that it can dramatically reduce computational complexity. Furthermore, the Visual Geometry Group (VGG) network is employed to evaluate the algorithm in practice. The results show that the proposed algorithm can provide the optimal performance by combining the savings of these two algorithms. It saves 75% of the runtime compared with the conventional algorithm.

scholarly journals Application of Deep Learning Networks to Segmentation of Surface of Railway Tracks

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4065
Author(s):  
Piotr Bojarczak ◽  
Waldemar Nowakowski
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Vision System ◽  
Gaussian Function ◽  
Railway Track ◽  
Learning Networks ◽  
Improve Performance ◽  
Speed Up ◽  
Visual Geometry

The article presents a vision system for detecting elements of railway track. Four types of fasteners, wooden and concrete sleepers, rails, and turnouts can be recognized by our system. In addition, it is possible to determine the degree of sleeper ballast coverage. Our system is also able to work when the track is moderately covered by snow. We used a Fully Convolutional Neural Network with 8 times upsampling (FCN-8) to detect railway track elements. In order to speed up training and improve performance of the model, a pre-trained deep convolutional neural network developed by Oxford’s Visual Geometry Group (VGG16) was used as a framework for our system. We also verified the invariance of our system to changes in brightness. To do this, we artificially varied the brightness of images. We performed two types of tests. In the first test, we changed the brightness by a constant value for the whole analyzed image. In the second test, we changed the brightness according to a predefined distribution corresponding to Gaussian function.

scholarly journals Training Convolutional Neural Network for Sketch Recognition on Large-Scale Dataset

2019 ◽  
pp. 82-89
Author(s):  
Wen Zhou ◽  
Jinyuan Jia
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Rapid Development ◽  
Handheld Devices ◽  
Sketch Recognition ◽  
Large Scale Dataset ◽  
Computer Vision Technology ◽  
Recognition Learning ◽  
Visual Geometry

With the rapid development of computer vision technology, increasingly more focus has been put on image recognition. More specifically, a sketch is an important hand-drawn image that is garnering increased attention. Moreover, as handheld devices such as tablets, smartphones, etc. have become more popular, it has become increasingly more convenient for people to hand-draw sketches using this equipment. Hence, sketch recognition is a necessary task to improve the performance of intelligent equipment. In this paper, a sketch recognition learning approach is proposed that is based on the Visual Geometry Group16 Convolutional Neural Network (VGG16 CNN). In particular, in order to diminish the effect of the number of sketches on the learning method, we adopt a strategy of increasing the quantity to improve the diversity and scale of sketches. Initially, sketch features are extracted via the pretrained VGG16 CNN. Additionally, we obtain contextual features based on the traverse stroke scheme. Then, the VGG16 CNN is trained using a joint Bayesian method to update the related network parameters. Moreover, this network has been applied to predict the labels of input sketches in order to automatically recognize the label of a sketch. Last but not least, related experiments are conducted, and the comparison of our method with the state-of-the-art methods is performed, which shows that our approach is superior and feasible

scholarly journals Recognition of Dog Breeds using Convolutional Neural Network and Visual Geometry Group

2019 ◽  
Vol 9 (1) ◽  
pp. 3898-3902
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Convolutional Neural Network ◽  
Exact Result ◽  
Cross Breeding ◽  
Naked Eye ◽  
Maximum Accuracy ◽  
Eye Recognition ◽  
Visual Geometry

Due to excessive breeding or cross-breeding, the nature of an animal like a dog has varied a lot from years ago. Using Image processing for the breed analysis will predict the exact result/s with maximum accuracy, unlike naked eye recognition ADA boosting methodology is used for breed analysis and recognition. ADA Boosting creates a strong classifier from several weak classifiers. To separate the dog breeds from one another, we use Image processing classification. It predicts the predominant breed/s present in the canine with maximum accuracy. Since the dogs may be cross-breed or had cross-breed predecessors, they may have a variety of breeds present in them, so using Image processing Classification tools we find the correct breed/s. It will be essential for easy classification of the dogs based on breeds and it can provide proof that naked eye recognition of breeds is undependable or trivial. Using Image processing analysis, we can analyze and do recognition of various animals like sheep, cattle, etc

scholarly journals One-Dimensional Convolutional Neural Network for Drill Bit Failure Detection in Rotary Percussion Drilling

Mining ◽  
2021 ◽  
Vol 1 (3) ◽  
pp. 297-314
Author(s):  
Lesego Senjoba ◽  
Jo Sasaki ◽  
Yoshino Kosugi ◽  
Hisatoshi Toriya ◽  
Masaya Hisada ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Failure Detection ◽  
Drill Bit ◽  
Mining Operations ◽  
One Dimensional ◽  
Rock Drill ◽  
Acceleration Sensors

Drill bit failure is a prominent concern in the drilling process of any mine, as it can lead to increased mining costs. Over the years, the detection of drill bit failure has been based on the operator’s skills and experience, which are subjective and susceptible to errors. To enhance the efficiency of mining operations, it is necessary to implement applications of artificial intelligence to produce a superior method for drill bit monitoring. This research proposes a new and reliable method to detect drill bit failure in rotary percussion drills using deep learning: a one-dimensional convolutional neural network (1D CNN) with time-acceleration as input data. 18 m3 of granite rock were drilled horizontally using a rock drill and intact tungsten carbide drill bits. The time acceleration of drill vibrations was measured using acceleration sensors mounted on the guide cell of the rock drill. The drill bit failure detection model was evaluated on five drilling conditions: normal, defective, abrasion, high pressure, and misdirection. The model achieved a classification accuracy of 88.7%. The proposed model was compared to three state-of-the-art (SOTA) deep learning neural networks. The model outperformed SOTA methods in terms of classification accuracy. Our method provides an automatic and reliable way to detect drill bit failure in rotary percussion drills.

scholarly journals APPLICATION OF A CONVOLUTIONAL NEURAL NETWORK AND A KOHONEN NETWORK FOR ACCELERATED DETECTION AND RECOGNITION OF OBJECTS IN IMAGES

2020 ◽  
Vol 4 ◽  
pp. 11-18
Author(s):  
Victor Skuratov ◽  
Konstantin Kuzmin ◽  
Igor Nelin ◽  
Mikhail Sedankin
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Satellite Image ◽  
Input Image ◽  
Underlying Surface ◽  
Convolutional Network ◽  
Kohonen Network ◽  
Recognition Of Objects ◽  
Areas Of Interest ◽  
Detection And Recognition

One of the most effective ways to improve the accuracy and speed of algorithms for searching and recognizing objects in images is to pre-select areas of interest in which it is likely to detect objects of interest. To determine areas of interest in a pre-processed radar or satellite image of the underlying surface, the Kohonen network was used. The found areas of interest are sent to the convolutional neural network, which provides the final detection and recognition of objects. The combination of the above methods allows to speed up the process of searching and recognizing objects in images, which is becoming more expedient due to the constantly growing volume of data for analysis. The process of preliminary processing of input data is described, the process of searching and recognizing patterns of aircraft against the underlying surface is presented, and the analysis of the results is carried out. The use of the Kohonen neural network makes it possible to reduce the amount of data analyzed by the convolutional network by 18–125 times, which accordingly accelerates the process of detection and recognition of the object of interest. The size of the parts of the input image fed into the convolutional network, into which the zones of interest are divided, is tied to the image scale and is equal to the size of the largest detectable object, which can significantly reduce the training sample. Application of the presented methods and centering of the object on training images allows accelerating the convolutional network training by more than 5 times and increasing the recognition accuracy by at least 10%, as well as minimizing the required minimum number of layers and neurons of the network by at least halving, respectively increasing its speed

Sign in / Sign up

Export Citation Format

Share Document