Inspection Line Research Articles

PSLBI-5 Ruminal papillae morphology of beef on dairy heifers with abscessed or non-abscessed livers

Abstract The ruminal papillae morphology characteristics of feedlot beef on dairy non-spayed heifers with liver abscess to those with non-abscessed liver were evaluated. Heifers were sourced from 27 lots which were harvested on six dates between November 2022 and February 2023. Upon harvest, a total of 94 rumen tissue samples from animals presenting liver abscesses and 110 rumen tissue samples from animals with non-abscessed livers were collected in pairs, as abscesses were identified within the harvesting facility viscera inspection line, following a randomized complete block design (block = lot within harvest date). Individual fragments (6 cm2) from the cranial sac epithelium of the rumen were collected, rinsed with deionized water, immersed in 70% alcohol, and preserved under refrigeration (4 oC) until analysis. Ruminal tissues were trimmed (1 cm2), in which the number of papillae was counted by three trained personnel, followed by the removal of 12 representative papillae specimens for further area electronic scanning (The University of Texas Health Science Center of San Antonio, Image Tool) to determine average papillae area, number per cm2 (AVP), average papillae area in cm2 (APA), absorptive surface area in cm2/fragment cm2 (ASA), and papillae absorptive surface area, % (ASA). Data were analyzed using the GLIMMIX procedures of SAS, with individual animal ruminal tissue used as the experimental unit, the fixed effect of ruminal condition, and the random effect of lot within the harvesting date. Average papillae number (P = 0.27), average papillae area (P = 0.74), absorptive surface area (P = 0.48), and papillae absorptive surface area (P = 0.43) were not affected by the presence of liver abscess. Severity of liver abscess distinguished as A -, A, or A+ scores compared with non-abscessed liver showed no difference on papillae number (P = 0.34), papillae area (P = 0.89), and absorptive area (P = 0.62). The presence of small or large liver abscesses did not affect the papillae area, size, or absorptive area (P ≥ 0.41). The liver lobe location of abscesses (cranial, caudal, both) did not affect (P ≥ 0.17) any of the ruminal morphological variables measured. The presence of liver abscesses, whether diffuse or localized, in beef on dairy heifers, did not affect (P ≥ 0.58) the development of ruminal papillae. The presence, severity, or location of liver abscess was not connected with ruminal papillae number, area, or absorptive surface area of beef on dairy heifers measured upon harvest time. The absence of ruminal papillae morphological changes in animals committed with liver abscesses may be further investigated with the characterization of potential cellular physical changes of the ruminal tissue and the integrity of the primary barrier in the digestive tract.

A Novel End-to-End Deep Learning Framework for Chip Packaging Defect Detection.

As semiconductor chip manufacturing technology advances, chip structures are becoming more complex, leading to an increased likelihood of void defects in the solder layer during packaging. However, identifying void defects in packaged chips remains a significant challenge due to the complex chip background, varying defect sizes and shapes, and blurred boundaries between voids and their surroundings. To address these challenges, we present a deep-learning-based framework for void defect segmentation in chip packaging. The framework consists of two main components: a solder region extraction method and a void defect segmentation network. The solder region extraction method includes a lightweight segmentation network and a rotation correction algorithm that eliminates background noise and accurately captures the solder region of the chip. The void defect segmentation network is designed for efficient and accurate defect segmentation. To cope with the variability of void defect shapes and sizes, we propose a Mamba model-based encoder that uses a visual state space module for multi-scale information extraction. In addition, we propose an interactive dual-stream decoder that uses a feature correlation cross gate module to fuse the streams' features to improve their correlation and produce more accurate void defect segmentation maps. The effectiveness of the framework is evaluated through quantitative and qualitative experiments on our custom X-ray chip dataset. Furthermore, the proposed void defect segmentation framework for chip packaging has been applied to a real factory inspection line, achieving an accuracy of 93.3% in chip qualification.

LOWERING CUSTOMER CLAIM &; NG RATIO ON JACK BRACKET PART USING LEAN SIX SIGMA-DMAIC METHOD AT PT. XYZ

PT. XYZ is a manufacturing company that produces Sub Assembly products for two-wheeled and four-wheeled vehicles. Broadly speaking, the stages of the Jack Bracket production process consist of five processes, namely the sharing stage in the Raw Material Line, the Stamping process in the Small Press Line, the Spot Welding Stage in the Welding Assy Line and the Checking Stage in the Final Inspection Line. This research was conducted at Line Assy Welding where the Line produces Jack Bracket parts and Line Final Inspection. Based on NG Outflow &; NG Ratio data in the period July to December 2023, 57 pcs of spot defects were obtained and the number of internal process defects was 32,325 PPM which is equivalent to sigma level 3.3. After applying the six sigma method, the number of NG Customer Claims is nil (0 pcs) and the level of product defects can be reduced to 7,500 PPM which is equivalent to sigma level 4.

Auto-Inspection System Using Optimized Fuzzy Sliding Mode Control Strategy for Tunnel Inspection

Cities composed of many mountainous areas necessitate the use of many tunnels for roads and highways with a potential safety hazard. To determine the safety of tunnels, periodic tunnel inspections mainly rely on manual work, which is dangerous and slow. Therefore, this paper proposes an auto-inspection system for tunnel inspection consisting of a robotic arm, laser sensors, and an inspection radar to free inspectors from hazardous environments and high-intensity work. Based on the mathematical model in the inspection process, a sliding mode controller is designed and optimized with fuzzy control and hyperbolic tangent functions, and is used in a tunnel inspection robot system for the first time. The simulation results show that optimized fuzzy sliding mode control can improve the tracking accuracy and stability during the tracking process compared with the traditional algorithm. Curved line inspection and arch line inspection experiment tests demonstrate that our system can automatically inspect the tunnel, and that the optimized fuzzy sliding mode control provides a superior performance in terms of the tracking process, with the average error decreasing by 37.8% when compared to traditional algorithms. Therefore, the proposed system is of great significance for high-precision and high-stability unmanned automated tunnel inspection.

On the use of a linear array EMAT for remote thickness gauging using the reflected modes on a steel pipe

Guided wave nondestructive testing refers to a set of fast and reliable techniques used to scan structures such as plates or pipes over medium to long range distances. The structural filtering method uses high-order modes and their cutoff frequency-thickness products to estimate the thickness along an inspection line. A corroded region, which can be approximated by a local loss of thickness, will act as a filter on the propagating modes. Because of their cutoff frequency-thickness product, some modes will not be able to propagate and will be either reflected or converted. Shear horizontal guided waves are the main candidate for structural filtering due to the simplicity of interpretation of their dispersion curves and their low sensitivity to non-viscous surface fluid loading. Electromagnetic acoustic transducers (EMAT) provide fast and efficient SH wave transduction but the most common designs, namely, periodic and permanent magnet EMAT is a mono element probe allowing modes to be excited only around a fixed wavelength. Recent work has shown that a linear array EMAT can be combined with a phase velocity excitation to allow almost complete control of the emitted waves in the frequency wavenumber space. In this paper, the linear array EMAT developed is used to estimate the minimum thickness of a defect machined on a 10.2 mm thick steel pipe with an external diameter of 323.8 mm. The measurements and finite element simulations carried out enabled us to estimate the thickness in several positions, with a maximum error of 0.4 mm and locate the defect with an error of 10 mm over a propagation distance of 600 mm.

Overlapped tobacco shred image segmentation and area computation using an improved Mask RCNN network and COT algorithm.

The classification of the four tobacco shred varieties, tobacco silk, cut stem, expanded tobacco silk, and reconstituted tobacco shred, and the subsequent determination of tobacco shred components, are the primary tasks involved in calculating the tobacco shred blending ratio. The identification accuracy and subsequent component area calculation error directly affect the composition determination and quality of the tobacco shred. However, tiny tobacco shreds have complex physical and morphological characteristics; in particular, there is substantial similarity between the expanded tobacco silk and tobacco silk varieties, and this complicates their classification. There must be a certain amount of overlap and stacking in the distribution of tobacco shreds on the actual tobacco quality inspection line. There are 24 types of overlap alone, not to mention the stacking phenomenon. Self-winding does not make it easier to distinguish such varieties from the overlapped types, posing significant difficulties for machine vision-based tobacco shred classification and component area calculation tasks. This study focuses on two significant challenges associated with identifying various types of overlapping tobacco shreds and acquiring overlapping regions to calculate overlapping areas. It develops a new segmentation model for tobacco shred images based on an improved Mask region-based convolutional neural network (RCNN). Mask RCNN is used as the segmentation network's mainframe. Convolutional network and feature pyramid network (FPN) in the backbone are replaced with Densenet121 and U-FPN, respectively. The size and aspect ratios of anchors parameters in region proposal network (RPN) are optimized. An algorithm for the area calculation of the overlapped tobacco shred region (COT) is also proposed, which is applied to overlapped tobacco shred mask images to obtain overlapped regions and calculate the overlapped area. The experimental results showed that the final segmentation accuracy and recall rates are 89.1% and 73.2%, respectively. The average area detection rate of 24 overlapped tobacco shred samples increases from 81.2% to 90%, achieving high segmentation accuracy and overlapped area calculation accuracy. This study provides a new implementation method for the type identification and component area calculation of overlapped tobacco shreds and a new approach for other similar overlapped image segmentation tasks.

Computer Vision Implementation in Scratch Inspection and Color Detection on The Car Roof Surface

The automotive industry in Indonesia is one of the important pillars in the manufacturing sector. High speed productivity and high-level quality of their products are required for increasing the company value. The car roof inspection is still in low speed and inadequate quality control method for most of the car company’s manufacturing production line. This inspection process is highly dependent to human expertise and skill of the assembly operators. This study purposes to increase the productivity in the inspection line by eliminate human error using computer vision. This research aims to find an automatic and accurate method for visual inspection of the color quality and scratch defect on car roof surfaces, using the data generated from the standardized database QR Code. The proposed solution uses MobileNet-SSD method of computer vision in recognizing scratch defects, while color detection of the roof is attained through hue saturation method. The study employs data capture from a camera and compares the amount of object inspected in real time. The scratch inspection with 70 image samples and 4000 training steps results in a 3.33% error with color detection and inspection success rate of 80%.

Histopathological and molecular methods as complementary diagnostic in case of lymphadenopathies suggestive of bovine tuberculosis.

Bovine tuberculosis (TB) is a chronically evolving zoonotic infectious disease caused by Mycobacterium bovis. Anatomopathological examination during post mortem inspection in bovines is the main resource engaged in sanitary slaughter; however, it is very troublesome since many granulomatous inflammatory processes have similar morphological characteristics. Thus, this study aims to use complementary diagnosis methods (histopathological and polymerase chain reaction - PCR assays) to confirm the macroscopic assessment of lymphadenopathies indicative of tuberculosis in bovines slaughtered in a refrigerated slaughterhouse in Tailândia city, PA, Brazil. Fifty‑one samples were collected from lesions indicative of tuberculosis in pre‑scapular and pre‑pectoral lymph nodes (or different lymphadenitis) in condemned carcasses. Histological processing employed routine techniques carried out at the Laboratory of Animal Pathology of the Federal Rural University of the Amazon, while the PCR assay was performed at the Bacteriology Laboratory of the Evandro Chagas Institute. Results showed that 1.96% of the histopathology samples corresponded to inflammatory processes typical of TB and that, in PCR, 4.25% of the samples had the amplification profile of the M. bovis species. These results indicate the importance of adding complementary methods to assist the sanitary inspection line and make inspection more efficient in its decisions.

Identificação molecular de genes de virulência de Escherichia coli e análise histopatológica em frangos condenados por aerossaculite

ABSTRACT: The present study identified virulence genes and pathological changes caused by Escherichia coli in chicken carcasses condemned for airsacculitis and assessed if the histopathological examination and polymerase chain reaction (PCR) were effective for studies like this. Trachea, liver, and lung were collected from 30 chickens with suspected airsacculitis that has been condemned in the inspection line. The samples were analyzed by PCR to simultaneously identify two virulence genes (iss and tsh genes) and for histopathological testing. PCR efficiently genotypically characterize the E. coli isolates, where the virulence genes iss and tsh were found in three birds simultaneously. The histopathological examination detected a predominance of heterophils and mononuclear cells in the trachea (100%), lung (90%), and liver (13.3%). The liver was the organ where practically no alteration was diagnosed. The results of multiplex PCR for the tsh and iss virulence genes indicate the great potential of the approach in the characterization of E. coli isolates. Unspecific identification did not occur, thus making it necessary to use technologies for the identification and prevention of this agent in aviaries and poultry abattoirs.

A novel image detection method for internal cracks in corn seeds in an industrial inspection line

Internal cracks produced on the inner endosperm side of corn seeds are difficult to identify. During actual production, the random falling of numerous corn seeds increases the difficulty of crack detection. To date, there has been little research on internal crack detection in corn seeds. This paper reports a new detection method that combines a deep learning algorithm with edge detection threshold processing. This method is based on the optimized S2ANet model. The Average Precision (AP) value of the optimized S2ANet model reached 95.6%, >9% higher than that of the original model. This method also involves novel methodological approaches for obtaining uniform seed direction. Experiments showed that it effectively solves the problems of random seed numbers, random seed orientations, different types of light source transmission, and difficulties in dataset production. In an experiment with individual seed types (cracked and non-cracked), the identification accuracy was 95.08% for cracked seeds and 95.75% for non-cracked seeds. In an experiment with a mixture of seed types, the average precision of 10 trials was 95.91%, the average recall was 94.8%, and the average F-score value (F1) was 95.34%. This level of accuracy is higher than that achieved through the direct use of deep learning detection algorithms. This study makes a valuable contribution to the detection of internal cracks in corn seeds on industrial inspection lines. At the same time, it provides a new approach for non-destructive testing of plant seeds.

A Decision Support System for Power Components Based on Improved YOLOv4-Tiny

The traditional image object detection algorithm applied in power inspection cannot effectively position power components, and the accuracy of recognition is low in scenes with some interference. In this research, we proposed a data-driven power detection method based on the improved YOLOv4-tiny model, which combined the ResNet-D module and the adjusted Res-CBAM to the backbone network of the existing YOLOv4-tiny module. We replaced the CSPOSANet module in the YOLOv4-tiny backbone network with the ResNet-D module to reduce the FLOPS required by the model. At the same time, the adjusted Res-CBAM whose feature fusion ways were replaced with stacking in the channels was combined as an auxiliary classifier. Finally, the features of five different receptive scales were used for prediction, and the display of the results was optimized by merging the prediction boxes. In the experiment, 57134 images collected on the power inspection line were processed and labeled, and the default anchor boxes were re-clustered, and the speed and accuracy of the model were evaluated by video and validation set of 3459 images. Processing multiple pictures and videos collected from the power inspection projects, we re-clustered the default anchor box and tested the speed and accuracy of the model. The results show that compared with the original YOLOv4-tiny model, the accuracy of our method that can position objects under occlusion and complex lighting conditions is guaranteed while the detection speed is about 13% faster.

Mycobacterium bovis detection in slaughtered pigs in the state of Rio Grande do Sul, Brazil

The infection by the Mycobacterium genus is important in pig farming due to the economic losses caused by total or partial carcass condemnation in slaughterhouses. The present study investigated the occurrence of a tuberculosis outbreak in pigs, based on the identification of lesions at the slaughter line of a slaughterhouse. At the inspection line of the slaughterhouse, carcasses were identified with viscera containing macroscopic lesions that indicated tuberculosis (granulomatous lymphadenitis). Tracheobronchial, mesenteric, and submandibular lymph nodes were collected, as well as liver samples and their corresponding lymph nodes. The samples were sent to the Federal Agricultural Defense Laboratory (LFDA/RS) and processed for the diagnosis of tuberculosis and the molecular characterization of Mycobacterium bovis. Based on the results of post-mortem and laboratory inspections, the occurrence was characterized as a tuberculosis outbreak in pigs, which originated from a farm in the state of Rio Grande do Sul, Brazil. Over three months, three batches, adding up to 2884 animals, were sent to slaughter, of which 102 (3.5%) had tuberculosis-like lesions at the inspection line. Based on these results, the productive process was investigated, assessing the feeding, water supply, and milk whey offered in the diet of pigs. It was concluded that the outbreak was caused by feeding unpasteurized or inadequately pasteurized (insufficient time x temperature relation) whey to the pigs. The use of whey from cheese production is a frequent practice in the state of Rio Grande do Sul and one of the risk factors for granulomatous lymphadenitis in pigs.

Security management of national park security in the border of Indonesia - Malaysia

Boundary is an important part of the state's sovereignty and becomes a fortress of all kinds of threats. The threat about security of natural resources is one of non-military threat which affects Indonesia’s security. Betung Kerihun National Park adjoins to Malaysia in northern of Indonesia, so it can be vulnerable to threats. The purposes of this research are to analyze the threat of security toward management of Betung Kerihun National Park (TNBK), the efforts made to overcome the security threat, and the management of TNBK on the border of Indonesia and Malaysia. The research uses qualitative method using in-depth interviews and later analyzing the primary and secondary data. The results show that the security threats of TNBK are agarwood stealing, gold mining, illegal logging, wildlife distribution, lack of security staff, no security forces (Satgas Pamtas) on the northern boundary of TNBK, and border patrol inspection line construction. The efforts to overcome security threats are preventive, pre-emptive, and repressive. The management of TNBK on the border of Indonesia and Malaysia in order to protect border security are including management functions of planning, organizing, leading (directing), and evaluating. The recommendations to overcome the security threat of national parks on the border between Indonesia and Malaysia are the active role of security forces and the establishment of buffer zone management.

Preparation and properties of fluorescent quantum dots microbeads encapsulated in-situ by polyisobornyl methacrylate for immunochromatography

In recent years, antibody-labeled fluorescent probes have attracted wide attention in fluorescence immunochromatography. Quantum dots (QDs) are excellent fluorescent materials with some unique optical properties, including strong stability against photobleaching, broad excitation spectra, high emission intensity, good fluorescence efficiency, and narrow excitonic emission. The CdSe/ZnS QDs microbeads were prepared by encapsulation in-situ of CdSe/ZnS QDs in polyisobornyl methacrylate (PIBOMA) herein and then functional QDs microbeads were produced by the binding of active carboxyl-modified QDs microbeads to the C-reactive protein (CRP) antibody. Their fluorescence properties were also investigated and functional QDs microbeads were further evaluated as fluorescent probes to detect different CRP concentrations using the fluorescence immunoassay test strips. The experiment data indicated that functional QDs microbeads possessed good stability, high fluorescence efficiencies, narrow fluorescence spectra, and good linear relationship of detection line signal versus quality inspection line signal (T1 / C) to the CRP concentration varying from 0.001 to 0.2 mg / l. Therefore, functional CdSe/ZnS QDs microbeads encapsulated in PIBOMA bioconjugated to CRP antibody can be used as the potential fluorescent probes to achieve quantitative detection in the immunochromatographic technology.

A high performance real-time vision system for curved surface inspection

Surface quality plays an important role in inspection lines. In this paper, a novel imaging device combined with FPGA (Field Programmable Gate Array) based processing platform had been designed to detect and analyse curved surface defects for vision inspection. The optical imaging part was made by an optical device which can be used to collect curved surface features without anamorphose and a camera with 70k Hz linear CMOS was used to capture surface information. The FPGA based inspection platform had been developed for camera control and image processing. Inspecting experiments had been tested with an inspection accuracy of 0.2 mm x 0.2 mm which satisfied a 12 m/s real-time vision inspection line. This research result can be subsequently applied to various surface inspection scenarios.

Design and Implementation of Electric Power Patrol Monitoring System Based on Beidou and Mobile Network

Most existing communication technologies used for power inspection systems cannot seamlessly cover the inspection line range. Therefore, the real-time transmission of inspection information and the safety of personnel are difficult to guarantee. Based on current research on electric power inspection and the industry’s urgent need for real-time and accurate location information of inspectors, this paper designed and developed an electric power patrol and monitoring system using the Beidou satellite system in conjunction with mobile networks. The problem of patrolling information in blind areas where ground communications cannot be reached in real time is effectively solved through a seamless switching design between Beidou short messages and mobile networks. The short message broadcast and high-precision position information return of inspection personnel were also realized by applying the Beidou multi-mode data transmission module as independently developed. The system took advantage of the user and function-oriented conceptual design and the Browser/Server (B/S)-based architecture design, as well as the combination with the SpringMVC + Spring + MyBatis (SSM) to improve the quality of the development process. Some key functions, such as real-time position display, track playback, user information management, and other functions, are interactive with the implemented visual user interfaces, which fundamentally helps the power monitoring department provide remote visual supervision services. The test results of the core module showed that the system could be used as a supplement to the power inspection and supervision industry, especially for deep mountain valleys, dense forests, and other areas without stable communication signals.

Anatomopathological characterization and etiology of lesions on Nile tilapia fillets (Oreochromis niloticus) caused by bacterial pathogens

Fish farming represents an important and healthy source of protein for human nutrition. Currently, Nile tilapia (Oreochromis niloticus) is the second most raised fish species worldwide, and its fillet plays an important role in the international trade of fish meat. In Brazil, fish slaughterhouses submitted to the Federal Meat Inspection Service detected lesions on tilapia fillets, which cause condemnation and economic losses to farmers and companies. The main etiologic agents associated with these fillet lesions have never been addressed. This study aimed to characterize the anatomopathology and etiologic agents involved in Nile tilapia fillet lesions. From May to September 2017, 70 fillets of Nile tilapia discarded as improper for human consumption at the inspection line were sampled, macroscopically characterized, and submitted to histopathology. In addition, Streptococcus agalactiae and Francisella noatunensis subsp. orientalis (Fno) were detected by PCR and qPCR, respectively. Out of all analyzed samples, 67% were positive either for Streptococcus agalactiae, Fno, or both. Three macroscopic patterns were identified, being two associated with bacterial pathogens. 85% of the Fno positive fillets had a black dot pattern and 90% of the S. agalactiae positive fillets had a cavity pattern on the surface of the fillet. Irregular white areas were not positive for any agent and were trauma related. The microscopic findings were pyogranulomatous and necrotizing myositis of varying degrees and distribution. The rate of discard in the lots affected by bacteria ranged from 0.2% to 2% of fillets. This is the first report of Fno as an important cause of fillet discharge in Nile tilapia slaughterhouses. The macroscopic patterns identified may be helpful in suggesting the etiology of these lesions and preventing economic loss.

Research on fault location of distribution network based on Radar principle

When the distribution network fails, the operation and maintenance personnel need to quickly determine the fault location and minimize the scope of the inspection line so that the fault repair personnel can accurately reach the vicinity of the fault point to carry out work. Whether the fault location method is advanced and reliable directly affects the power failure time of the power supply user, and further affects the social, economic, and life aspects. Therefore, the fault location of the distribution network needs to satisfy both reliability and accuracy. It is the basis and premise for troubleshooting, isolating and restoring the power supply. The automation level of China’s distribution network is relatively backward, and the reliability of power supply equipment is relatively low, making it difficult to find fault points. If we find out the intelligent algorithms that can meet the requirements of rapid positioning, accuracy and fault tolerance through theoretical research, we can Improve the fault location efficiency very well.

Correction to: Distribution Line Pole Detection and Counting Based on YOLO Using UAV Inspection Line Video

The article “Distribution Line Pole Detection and Counting Based on YOLO Using UAV Inspection Line Video“, written by Binghuang Chen and Xiren Miao was originally published.

Distribution Line Pole Detection and Counting Based on YOLO Using UAV Inspection Line Video

In order to improve the efficiency of post-disaster treatment of power distribution network, the application of UAV in disaster reduction and relief has been paid much attention by the power sector. Aiming at the loss assessment needs of overhead transmission lines in distribution network, this paper proposes an innovative solution of pole detection and counting in distribution network based on UAV inspection line video. Combined with the characteristics of YOLO’s rapid detection, the convolution neural network is applied to the image detection of the pole state. In addition, the pole data and corresponding images are obtained at the same time of detecting the inspection line video. Therefore, the power department can quickly count the losses to cope with the disaster. The anchor value is modified before image training by YOLO v3, and sets the corresponding ROI for the UAV inspection line standard. In order to quickly obtain the loss assessment of post-disaster pole lodging, this paper proposes a counting algorithm by using the continuous ordinate change of the bounding box of the same pole in front and rear frame of video, so that the classified counting of pole is accurate and the detection precision is above 0.9. The results obtained in video test show that this method is effective in detecting and counting the state of the pole of overhead transmission line in distribution network.