Abstract

The objective of this thesis was to evaluate the viability of implementation of an object recognition algorithm driven by deep learning for aerospace manufacturing, maintenance and assembly tasks. Comparison research has found that current computer vision methods such as, spatial mapping was limited to macro-object recognition because of its nodal wireframe analysis. An optical object recognition algorithm was trained to learn complex geometric and chromatic characteristics, therefore allowing for micro-object recognition, such as cables and other critical components. This thesis investigated the use of a convolutional neural network with object recognition algorithms. The viability of two categories of object recognition algorithms were analyzed: image prediction and object detection. Due to a viral epidemic, this thesis was limited in analytical consistency as resources were not readily available. The prediction-class algorithm was analyzed using a custom dataset comprised of 15 552 images of the MaxFlight V2002 Full Motion Simulator’s inverter system, and a model was created by transfer-learning that dataset onto the InceptionV3 convolutional neural network (CNN). The detection-class algorithm was analyzed using a custom dataset comprised of 100 images of two SUVs of different brand and style, and a model was created by transfer-learning that dataset onto the YOLOv3 deep learning architecture. The tests showed that the object recognition algorithms successfully identified the components with good accuracy, 99.97% mAP for prediction-class and 89.54% mAP. For detection-class. The accuracies and data collected with literature review found that object detection algorithms are accuracy, created for live -feed analysis and were suitable for the significant applications of AVI and aircraft assembly. In the future, a larger dataset needs to be complied to increase reliability and a custom convolutional neural network and deep learning algorithm needs to be developed specifically for aerospace assembly, maintenance and manufacturing applications.

Highlights

  • The main objective of this thesis was to test the viability of object recognition algorithms for the implementation into manufacturing, assembly and maintenance tasks

  • The prediction-class algorithm was analyzed using a custom dataset comprised of 15 552 images of the MaxFlight V2002 Full Motion Simulator’s inverter system, and a model was created by transfer-learning that dataset onto the InceptionV3 convolutional neural network (CNN)

  • The detection-class algorithm was analyzed using a custom dataset comprised of 100 images of two SUVs of different brand and style, and a model was created by transfer-learning that dataset onto the YOLOv3 deep learning architecture

Read more

Summary

Introduction

The main objective of this thesis was to test the viability of object recognition algorithms for the implementation into manufacturing, assembly and maintenance tasks. Artificial Intelligence has various applications across various industries; it is young to aerospace industry Large companies such as Boeing and Airbus have recently started to utilize object recognition in system inspections. The primary objective and secondary objectives, such as cloud-based dataset storage and model creation, were taken into consideration to design and implement algorithms that recognize a mean accuracy persicion (mAP) of 90% and 85% for prediction-class and detection-class, respectively. Deep learning CNNs require large amounts of images and annotations for an accurate model to be created This is achieved by large corporations due to the quantity of researchers and amount of time. For the proof of concept, this thesis used undersized and under-diversified datasets comprised of aerospace and manufacturing industry-related components

Computer Vision and Deep Learning
Scope and Structure of the Thesis
Background
Convolutional Neural Networks
Overview of Dataset Format and Compared CNNs
Current Commercial Application
Algorithm Design
Design Objectives
Design Requirements and Verifications
Objective
Methodology
Ground Station Setup
Dataset Collection and Preparation
Prediction-class
Experiments
Detection-class
1 2 3 4 5 6 7 8 9 10 11 12 13 15 17 20 21 22 23 25 30 38 58 62 70 81 93 Experiments
Degree of Requirements Matrix
Conclusion
Future Considerations
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call