Classification of Car Parts Using Deep Neural Network

Khanal, Salik Ram; Amorim, Eurico Vasco; Filipe, Vítor

doi:10.1007/978-3-030-58653-9_56

Cited by 7 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, to achieve our goal of addressing these issues via the replacement of the paper conformity list with a digital counterpart, our hybrid quality control support tool must [10,26,27]:…”

Section: System Architecturementioning

confidence: 99%

“…Thus, it avoids dependence on a list of real vehicles, ordered by the clients, that might not contain enough diversity for this test's purposes. The simulator uses the previously developed kSim9 [10,27] to generate the list of 6 conforming kSim9 vehicles (3 Citroën and 3 Peugeot, 3 commercial and 3 private models) and adds the predetermined nonconformities (tire covers, brand and model logos) to some of them. It also generates the vehicle's barcode with the ZXing plugin [43].…”

Section: Information Visualizationmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Quality Inspection for the Automotive Industry: Replacing the Paper-Based Conformity List through Semi-Supervised Object Detection and Simulated Data

et al. 2022

Self Cite

View full text Add to dashboard Cite

The still prevalent use of paper conformity lists in the automotive industry has a serious negative impact on the performance of quality control inspectors. We propose instead a hybrid quality inspection system, where we combine automated detection with human feedback, to increase worker performance by reducing mental and physical fatigue, and the adaptability and responsiveness of the assembly line to change. The system integrates the hierarchical automatic detection of the non-conforming vehicle parts and information visualization on a wearable device to present the results to the factory worker and obtain human confirmation. Besides designing a novel 3D vehicle generator to create a digital representation of the non conformity list and to collect automatically annotated training data, we apply and aggregate in a novel way state-of-the-art domain adaptation and pseudo labeling methods to our real application scenario, in order to bridge the gap between the labeled data generated by the vehicle generator and the real unlabeled data collected on the factory floor. This methodology allows us to obtain, without any manual annotation of the real dataset, an example-based F1 score of 0.565 in an unconstrained scenario and 0.601 in a fixed camera setup (improvements of 11 and 14.6 percentage points, respectively, over a baseline trained with purely simulated data). Feedback obtained from factory workers highlighted the usefulness of the proposed solution, and showed that a truly hybrid assembly line, where machine and human work in symbiosis, increases both efficiency and accuracy in automotive quality control.

show abstract

Section: System Architecturementioning

confidence: 99%

Section: Information Visualizationmentioning

confidence: 99%

Hybrid Quality Inspection for the Automotive Industry: Replacing the Paper-Based Conformity List through Semi-Supervised Object Detection and Simulated Data

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…As we can see, by reducing the former conformity list to its vehicle barcode and having its information wirelessly accessible through the factory's network, each workstation can access the database and only fetch the relevant information for their respective quality assessment. For ours we intend to have several mounted cameras set up at the entrance of the line and have the computer vision algorithm automatically detect a set of components [16,17]. The classification results are then compared with those on the database to generate a 3D representation of the vehicle.…”

Section: Design Of the Quality Control Support Toolmentioning

confidence: 99%

Worker Support and Training Tools to Aid in Vehicle Quality Inspection for the Automotive Industry

Campaniço

Khanal

Paredes

et al. 2021

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

In the competitive automotive market, where extremely high-quality standards must be ensured independently of the growing product and manufacturing complexity brought by customization, reliable and precise detection of any non-conformities before the vehicle leaves the assembly line is paramount. In this paper we propose a wearable solution to aid quality control workers in the detection, visualization and relay of any non-conformities, while also reducing known performance issues such as skill gaps and fatigue, and improving training methods. We also explore how the reliability, precision and validity tests of the visualization module of our framework were performed, guaranteeing a 0% chance occurrence of undesired non-conformities in the following usability tests and training simulator.

show abstract

“…This task is usually done by experienced operators in a manual way, who still rely on paper-based conformity lists as a tool to check the special features of each car and their own expertise. The conformity lists present a description in text format of all the vehicle features and components, which the workers read and compare with the assembled product [4]. However, mental and physical fatigue and the lack of experienced operators can compromise the task.…”

Section: Introductionmentioning

confidence: 99%

Conformity Assessment of Informative Labels in Car Engine Compartment with Deep Learning Models

Ferreira

Barroso

Filipe

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Industry 4.0 has been changing and improving the manufacturing processes. To embrace these changes, factories must keep up to date with all the new emerging technologies. In the automotive industry, the growing demand for customization and constant car model changes leads to an inevitable grow of complexity of the final product quality inspection process. In the project INDTECH 4.0, smart technologies are being explored in an automotive factory assembly line to automate the vehicle quality control, which still relies on human inspection based on paper conformity checklists. This paper proposes an automated inspection process based on computer vision to assist operators in the conformity assessment of informative labels affixed inside the engine compartment of the car. Two of the most recent object detection algorithms: YOLOv5 and YOLOX are evaluated for the identification of labels in the images. Our results show high mean average precision on both algorithms (98%), which overall, tells us that both algorithms showed good performances and have potential to be implemented in the shop floor to support the vehicle quality control.

show abstract

Classification of Car Parts Using Deep Neural Network

Cited by 7 publications

References 11 publications

Hybrid Quality Inspection for the Automotive Industry: Replacing the Paper-Based Conformity List through Semi-Supervised Object Detection and Simulated Data

Hybrid Quality Inspection for the Automotive Industry: Replacing the Paper-Based Conformity List through Semi-Supervised Object Detection and Simulated Data

Worker Support and Training Tools to Aid in Vehicle Quality Inspection for the Automotive Industry

Conformity Assessment of Informative Labels in Car Engine Compartment with Deep Learning Models

Contact Info

Product

Resources

About