Approach to Automated Visual Inspection of Objects Based on Artificial Intelligence

The article discusses the possibility of object detector usage in field of automated visual inspection for objects with specific parameters, specifically various types of defects occurring on the surface of a car tire. Due to the insufficient amount of input data, as well as the need to speed up the development process, the Transfer Learning principle was applied in a designed system. In this approach, the already pre-trained convolutional neural network AlexNet was used, subsequently modified in its last three layers, and again trained on a smaller sample of our own data. The detector used in the designed camera inspection system with the above architecture allowed us to achieve the accuracy and versatility needed to detect elements (defects) whose shape, dimensions and location change with each occurrence. The design of a test facility with the application of a 12-megapixel monochrome camera over the rotational table is briefly described, whose task is to ensure optimal conditions during the scanning process. The evaluation of the proposed control system with the quantification of the recognition capabilities in the individual defects is described at the end of the study. The implementation and verification of such an approach together with the proposed methodology of the visual inspection process of car tires to obtain better classification results for six different defect classes can be considered as the main novel feature of the presented research. Subsequent testing of the designed system on a selected batch of sample images (containing all six types of possible defect) proved the functionality of the entire system while the highest values of successful defect detection certainty were achieved from 85.15% to 99.34%.

Exposure of FeCrAl Overlay Welds on Superheater Tubes: Influence of Local Environment on Degradation

Two experimental FeCrAl alloy overlay welds on tube shields were exposed in the superheater of a full-size waste fired boiler for 6 months. The tube shields were in different tube lines and positions within the superheater chamber to investigate possible heterogeneities in the exposure environment. The visual inspection of the exposed tube shields and the corrosion-erosion rates calculated from the analysis of cross-sections showed that the mid-length roof location experienced the most aggressive environment. The compositional differences between the two experimental alloys were not found to be determinant in their performance under these specific exposure conditions. It was concluded that erosion had a decisive influence on the results. The identification of local differences within the superheater chamber is important when deciding on the material selection for the different areas and locations to be protected. The output of this study is therefore interesting for further design consideration of superheaters as well as for future planning of exposures.

Systematic visual analysis of groundwater hydrographs: potential benefits and challenges

Visual analysis of time series in hydrology is frequently seen as a crucial step to becoming acquainted with the nature of the data, as well as detecting unexpected errors, biases, etc. Human eyes, in particular those of a trained expert, are well suited to recognize irregularities and distinct patterns. However, there are limits as to what the eye can resolve and process; moreover, visual analysis is by definition subjective and has low reproducibility. Visual inspection is frequently mentioned in publications, but rarely described in detail, even though it may have significantly affected decisions made in the process of performing the underlying study. This paper presents a visual analysis of groundwater hydrographs that has been performed in relation to attempts to classify groundwater time series as part of developing a new concept for prediction in data-scarce groundwater systems. Within this concept, determining the similarity of groundwater hydrographs is essential. As standard approaches for similarity analysis of groundwater hydrographs do not yet exist, different approaches were developed and tested. This provided the opportunity to carry out a comparison between visual analysis and formal, automated classification approaches. The presented visual classification was carried out on two sets of time series from central Europe and Fennoscandia. It is explained why and where visual classification can be beneficial but also where the limitations and challenges associated with the approach lie. It is concluded that systematic visual analysis of time series in hydrology, despite its subjectivity and low reproducibility, should receive much more attention.

Association of Husband Support With Visual Inspection With Acetic Acid in Tamalanrea Health Care Makassar

Data World Health Organization (WHO) kejadian kanker serviks kanker pada wanita dengan perkiraan 570.000 kasus tahun 2018. Riskesdas 2013, prevalensi kanker serviks terdapat 5.349 kasus (12,8%). Tahun 2015 program deteksi dini kanker serviks berjalan pada 1.986 puskesmas di 304 kabupaten/kota provinsi di Indonesia. Dinas kesehatan provinsi Sulawesi selatan 24 kabupaten 440 puskesmas, perempuan dengan usia 30-49 tahun sebanyak 180.821 jiwa yang melakukan pemeriksaan IVA hanya sebanyak 882 wanita (0,49%). Puskesmas Tamalanre Makassar, jumlah Pasangan Usia Subur 306 orang. wanita yang melakukan test IVA pada tahun 2018 terdapat 3 wanita. Tujuan penelitian ini untuk mengetahui hubungan dukungan suami dengan pemeriksaan Inspeksi Visual Asam Asetat (IVA) pada Pasangan Usia Subur (PUS) di Puskesmas Tamalanrea Makassar. Jenis penelitian adalah penelitian kuantitatif, dengan menggunakan desain penelitian cross sectional dengan menggunakan uji fisher exact. Dengan jumlah sampel sebanyak 75 responden, pengambilan sampel dengan teknik purposive sampling menggunakan instrument penelitian kuesioner. Hasil penelitian didapatkan nilai ρ = 0.000 (ρ < α (0,05), menunjukkan bahwa ada hubungan dukungan suami dengan pemeriksaan Inspeksi Visual Asam Asetat (IVA) pada Pasangan Usia Subur (PUS) yang berarti hipotesis diterima. Simpulan dari penelitian ini terdapat hubungan dukungan suami dengan pemeriksaan Inspeksi Visual Asam Asetat (IVA) pasangan usia subur (PUS) di Puskesmas Tamalanrea Makassar. Disarankan agar peningkatan literasi dan edukasi dilakukan oleh fasyankes kepada para suami untuk memberikan dukungan kepada pasangan dalam pemeriksaan IVA.

Physics-Based Graphics Models in 3D Synthetic Environments as Autonomous Vision-Based Inspection Testbeds

Manual visual inspection of civil infrastructure is high-risk, subjective, and time-consuming. The success of deep learning and the proliferation of low-cost consumer robots has spurred rapid growth in research and application of autonomous inspections. The major components of autonomous inspection include data acquisition, data processing, and decision making, which are usually studied independently. However, for robust real-world applicability, these three aspects of the overall process need to be addressed concurrently with end-to-end testing, incorporating scenarios such as variations in structure type, color, damage level, camera distance, view angle, lighting, etc. Developing real-world datasets that span all these scenarios is nearly impossible. In this paper, we propose a framework to create a virtual visual inspection testbed using 3D synthetic environments that can enable end-to-end testing of autonomous inspection strategies. To populate the 3D synthetic environment with virtual damaged buildings, we propose the use of a non-linear finite element model to inform the realistic and automated visual rendering of different damage types, the damage state, and the material textures of what are termed herein physics-based graphics models (PBGMs). To demonstrate the benefits of the autonomous inspection testbed, three experiments are conducted with models of earthquake damaged reinforced concrete buildings. First, we implement the proposed framework to generate a new large-scale annotated benchmark dataset for post-earthquake inspections of buildings termed QuakeCity. Second, we demonstrate the improved performance of deep learning models trained using the QuakeCity dataset for inference on real data. Finally, a comparison of deep learning-based damage state estimation for different data acquisition strategies is carried out. The results demonstrate the use of PBGMs as an effective testbed for the development and validation of strategies for autonomous vision-based inspections of civil infrastructure.

Identification and Quantification of Microplastics in Aquaculture Environment

The existence of microplastics (MPs) poses a potential threat to the entire ecosystem and has gained wide public attention. As an essential source of aquatic products, aquaculture industries are inevitably subjected to the pollution of MPs, particularly when the plastic products are widely used in aquaculture. Even so, the identification of MPs in aquaculture is rarely reported. Hence, high-efficient analytical methods for accurate detection of MPs in the aquaculture environment are of utmost significance. This review comprehensively summarizes the analytical methods for MPs in aquaculture, including sampling, extraction, and qualitative and quantitative analyses of MPs. MPs are identified and quantified mainly by visual inspection, spectroscopy, or thermal analysis. In addition, this review also points out the limitations of these methods and the accuracy of quality control. Finally, the need for establishing standard methods is emphasized, and suggestions for future research are also proposed.

Post-Earthquake Rapid Damage Assessment of Road Bridges in Glina County

In December 2020, a strong earthquake occurred in Northwestern Croatia with a magnitude of ML = 6.3. The epicenter of this earthquake was located in the town of Petrinja, about 50 km from Zagreb, and caused severe structural damage throughout Sisak-Moslavina county. One of the biggest problems after this earthquake was the structural condition of the bridges, especially since most of them had to be used immediately for demolition, rescue, and the transport of mobile housing units in the affected areas. Teams of civil engineers were quickly formed to assess the damage and structural viability of these bridges and take necessary actions to make them operational again. This paper presents the results of the rapid post-earthquake assessment for a total of eight bridges, all located in or around the city of Glina. For the assessment, a visual inspection was performed according to a previously established methodology. Although most of the inspected bridges were found to be deteriorated due to old age and lack of maintenance, very few of them showed serious damage from the earthquake, with only one bridge requiring immediate strengthening measures and use restrictions. These measurements are also presented in this paper.

Longitudinal Stent Deformation in Undeployed Stents: A Case Series

Longitudinal stent deformation (LSD) is a recently reported problem with newer generation stents. The modification of stent materials and designs to make them more deliverable and conformable, as well as a focused approach in retaining their radial strength, has compromised longitudinal strength in currently available stents. Additionally, enhanced stent radiopacity, improved fluoroscopy, and heightened awareness have led to an increased incidence rate of the potentially under-recognized problem of LSD. Although originally described in deployed stents, LSD is being recognized in undeployed stents too. With available data to suggest an increased rate of adverse cardiac events like stent thrombosis and in-stent restenosis with LSD in deployed stents, an attempt to retrieve an undeployed deformed stent appears justified. We report 3 cases of LSD in undeployed stents and discuss its recognition. We also discuss the retrieval and visual inspection of retrieved stents and the simultaneous completion of coronary interventions via a double guide technique.