| 1. |
- Gaudiuso, Caterina, et al.
(författare)
-
Incubation effect in burst mode fs-laser ablation of stainless steel samples
- 2018
-
Ingår i: Proceedings of SPIE, the International Society for Optical Engineering. - : SPIE. - 0277-786X .- 1996-756X. ; 10520
-
Tidskriftsartikel (refereegranskat)abstract
- We report on an experimental study of the incubation effect during irradiation of stainless steel targets with bursts of femtosecond laser pulses at 1030 nm wavelength and 100 kHz repetition rate. The bursts were generated by splitting the pristine 650-fs laser pulses using an array of birefringent crystals which provided time separations between sub-pulses in the range from 1.5 ps to 24 ps. We measured the threshold fluence in Burst Mode, finding that it strongly depends on the bursts features. The comparison with Normal Pulse Mode revealed that the existing models introduced to explain the incubation effect during irradiation with trains of undivided pulses has to be adapted to describe incubation during Burst Mode processing. In fact, those models assume that the threshold fluence has a unique value for each number of impinging pulses in NPM, while in case of BM we observed different values of threshold fluence for fixed amount of sub-pulses but different pulse splitting. Therefore, the incubation factor coefficient depends on the burst features. It was found that incubation effect is higher in BM than NPM and that it increases with the number of sub-pulses and for shorter time delays within the burst. Two-Temperature-Model simulations in case of single pulses and bursts of up to 4 sub-pulses were performed to understand the experimental results. © Copyright SPIE.
|
|
| 2. |
- Lindgren, Erik, 1980, et al.
(författare)
-
Analysis of industrial X-ray computed tomography data with deep neural networks
- 2021
-
Ingår i: Proceedings of SPIE - The International Society for Optical Engineering. - : SPIE. - 0277-786X .- 1996-756X. ; 11840
-
Konferensbidrag (refereegranskat)abstract
- X-ray computed tomography (XCT) is increasingly utilized industrially at material- and process development as well as in non-destructive quality control; XCT is important to many emerging manufacturing technologies, for example metal additive manufacturing. These trends lead to increased needs of safe automatic or semi-automatic data interpretation, considered an open research question for many critical high value industrial products such as within the aerospace industry. By safe, we mean that the interpretation is not allowed to unawarely or unexpectedly fail; specifically the algorithms must react sensibly to inputs dissimilar to the training data, so called out-of-distribution (OOD) inputs. In this work we explore data interpretation with deep neural networks to address: robust safe data interpretation which includes a confidence estimate with respect to OOD data, an OOD detector; generation of realistic synthetic material aw indications for the material science and nondestructive evaluation community. We have focused on industrial XCT related challenges, addressing difficulties with spatially correlated X-ray quantum noise. Results are reported on training auto-encoders (AE) and generative adversarial networks (GAN), on a publicly available XCT dataset of additively manufactured metal. We demonstrate that adding modeled X-ray noise during training reduces artefacts in the generated imperfection indications as well as improves the OOD detector performance. In addition, we show that the OOD detector can detect real and synthetic OOD data and still model the accepted in-distribution data down to the X-ray noise levels.
|
|
| 3. |
- Lindgren, Erik, et al.
(författare)
-
Deep-learning-based out-of distribution data detection in visual inspection images
- 2023
-
Ingår i: Proceedings Of Spie 12489, NDE 4.0, Predictive Maintenance, Communication, and Energy Systems. - : Spie Digital Library. ; 12489
-
Konferensbidrag (refereegranskat)abstract
- Within quality critical industries, e.g. aerospace, quality control with non-destructive evaluation (NDE) is essential. The surface quality is often important and e.g. visual inspection is often applied. Part of the inspection is the data interpretation, not easily made automatic for critical products. Recent studies on the automatization have indicated promising results utilizing deep-learning-based artificial intelligence. However, many such algorithms are known to be overconfident when subjected to unexpected input (e.g. new/rare material defects) far from the training dataset, so-called out-of-distribution (OOD) data. We claim that safe computer-based interpretation of NDE data within quality critical applications, must respond sensible also to OOD data. A sensible response could be that the algorithms identify such OOD data and forward it to a human for further analysis. Such an OOD detector could facilitate a human-machine collaboration in a NDE 4.0 vision. In this work we have explored if a recently proposed (for industrial x-ray images) auto-encoder-based approach can be utilized as OOD detector (one-class classifier) for visual inspection data. The model is trained in an unsupervised manner on accepted input to reconstruct it at high precision. Simultaneously it is trained to remove synthetically added defect indications to generate a clean image patch, similar to denoising-auto-enoders. The difference between the input and reconstructed input is analyzed for OOD detection. We train and test the algorithm on a publicly available visual inspection dataset with surface defects. We achieve true positive rates at 0.90 with true negative rates at 0.99 and demonstrate detection of OOD data.
|
|
| 4. |
- Volpe, Annalisa, et al.
(författare)
-
Fabrication and assembling of a microfluidic optical stretcher polymeric chip combining femtosecond laser and micro injection molding technologies
- 2017
-
Ingår i: Proceedings of SPIE, the International Society for Optical Engineering. - : SPIE. - 0277-786X .- 1996-756X. ; 10092
-
Tidskriftsartikel (refereegranskat)abstract
- Microfluidic optical stretchers are valuable optofluidic devices for studying single cell mechanical properties. These usually consist of a single microfluidic channel where cells, with dimensions ranging from 5 to 20 Όm are trapped and manipulated through optical forces induced by two counter-propagating laser beams. Recently, monolithic optical stretchers have been directly fabricated in fused silica by femtosecond laser micromachining (FLM). Such a technology allows writing in a single step in the substrate volume both the microfluidic channel and the optical waveguides with a high degree of precision and flexibility. However, this method is very slow and cannot be applied to cheaper materials like polymers. Therefore, novel technological platforms are needed to boost the production of such devices on a mass scale. In this work, we propose integration of FLM with micro-injection moulding (ΌIM) as a novel route towards the cost-effective and flexible manufacturing of polymeric Lab-on-a-Chip (LOC) devices. In particular, we have fabricated and assembled a polymethylmethacrylate (PMMA) microfluidic optical stretcher by exploiting firstly FLM to manufacture a metallic mould prototype with reconfigurable inserts. Afterwards, such mould was employed for the production, through ΌIM, of the two PMMA thin plates composing the device. The microchannel with reservoirs and lodgings for the optical fibers delivering the laser radiation for cell trapping were reproduced on one plate, while the other included access holes to the channel. The device was assembled by direct fs-laser welding, ensuring sealing of the channel and avoiding thermal deformation and/or contamination. © 2017 SPIE.
|
|
