Browsing by Author "Lopes, Miguel"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- A Deep Learning Approach for PV Failure Mode Detection in Infrared Images: First InsightsPublication . Rocha, Daniel; Lopes, Miguel; Teixeira, Jennifer P.; Fernandes, Paulo A.; Morais, Modesto; Salome, Pedro M. P.Large-scale solar power plants require cheap and quick inspections, for this unmanned aerial vehicle (UAV's) for high resolution optical and infrared imaging were introduced in the past years. While using UAV’s is fast for image acquisition, image is a time-consuming process where the best of practice today is still for an expert to individually analyze each image. As such, in this work we use computer vision to accelerate this process. We performed an instance segmentation assessment using a pretrained mask R-CNN for the segmentation of defective modules, and cells, as well as for segmentation and classification of failures. This method was chosen due its good past performance. In this work we created a database from a solar power plant consisting of 42048 modules and an expert analyzed the images. Later on, our computer algorithm results were benchmarked against the expert. Our algorithm achieved a mean average precision (mAP) in defective module segmentation mask of 72.1 % and 47.9 % in segmentation mask of failure type with an intersection over union threshold (IoU) of 0.50, without human interference. The presented preliminary results allow to assess the methodology advantages and drawbacks to increase performance and pave the way to a large-scale study.
- Lean and Six Sigma Philosophies and Organizational Performance: A Study in Portuguese LaboratoriesPublication . Lima, Vanda; Craveiro, Andreia; Santos, Gilberto; Sá, José Carlos; Lopes, Miguel; Carvalho, José DinisPurpose: This research aimed to make a diagnosis of the implementation of Lean and Six Sigma philosophies in Portuguese laboratories and to evaluate the impact of these philosophies on organizational performance. Methodology/Approach: A quantitative research methodology was used, based on the survey research strategy, and using as data collection instrument an original online questionnaire, validated and distributed to the Portuguese laboratories via email. The sample was composed by 106 laboratories. Descriptive and inferential statistical analysis were applied to the data, using IBM SPSS software. Findings: It was found that most laboratories do not know the Lean Approach and/or Six Sigma philosophies, and their implementation occurred in about one tenth of the sample. The laboratories that implemented the philosophies were found to have a larger number of employees and turnover. Finally, regarding organizational performance it was found to be superior in laboratories that implemented at least one of the philosophies when compared to laboratories that did not implement any Lean and/or Six Sigma philosophy. Research Limitation/Implication: The small sample size, which corresponds to approximately 15% of the population, is the main limitation of the study. Originality/Value of paper: This study is the first diagnosis on the application of Lean and Six Sigma philosophies made in the Portuguese laboratory market, and may provide relevant inputs for decision-making in this context. Category: Research paper