Sandblasting Defect Inspection of Investment Castings Based on Deep Convolutional Neural Network

Investment castings often have surface impurities and pieces of shell molds can remain on the surface after sandblasting. Identification of defects involves time-consuming manual inspections in working environments of high noise and poor air quality. To reduce labor costs and increase the health and safety of employees, we applied automated optical inspection (AOI) combined with a deep learning framework based on convolutional neural networks (CNNs) to the detection of sandblasting defects. We applied the following four classic CNN models for training and predictive classification: AlexNet, VGG-16, GoogLeNet, and ResNet-34. In terms of predictive classification, AlexNet, VGG-16, and GoogLeNet v1 could accurately determine whether there were defects. Among the four models, AlexNet was the most accurate, with prediction accuracy of 99.53% for qualifying products and 100% for defective products. We demonstrate a direct detection technique based on the AOI and CNN structure with a fast and flexible computational interface.

Optical Material Characterisation of Prepreg CFRP for Improved Composite Inspection

Automated fibre layup techniques are often applied for the production of complex structural components. In order to ensure a sufficient component quality, a subsequent visual inspection is necessary, especially in the aerospace industry. The use of automated optical inspection systems can reduce the inspection effort by up to 50 %. Laser line scan sensors, which capture the topology of the surface, are particularly advantageous for this purpose. These sensors project a laser beam at an angle onto the surface and detect its position via a camera. The optical properties of the observed surface potentially have a great influence on the quality of the recorded data. This is especially relevant for dark or highly scattering materials such as Carbon Fiber Reinforced Plastics (CFRP). For this reason, in this study we investigate the optical reflection and transmission properties of the commonly used Hexel HexPly 8552 IM7 prepreg CFRP in detail. Therefore, we utilise a Gonioreflectometer to investigate such optical characteristics of the material with respect to different fibre orientations, illumination directions and detection angles. In this way, specific scattering information of the material in the hemispherical space are recorded. The major novelty of this research are the findings about the scattering behaviour of the fibre composite material which can be used as a more precise input for the methods of image data quality assessment from our previous research and thus is particularly valuable for developers and users of camera based inspection systems for CFRP components.

Development of a mobile, automated, optical inspection system for radioactive barrels

Due to the delayed construction and commissioning of a German repository for intermediate- and low-level radioactive waste, waste inventories from several decades are now located at the interim storage sites, the safe custody of which must also be ensured for an indefinite period of interim storage. The usual practice in the interim storage facilities is recurrent inspections, which are carried out almost exclusively manually and without electronic comparative recordings as well as without mechanical documentation and archiving. Remote or automated inspection does not take place. The inspections are carried out visually and are therefore very subjective and thus subject to errors. Manual performance is labor intensive and requires the use of personnel exposed to radiation. Neither are uniform inspection criteria of the visual inspections applied, nor are the inspections performed uniformly between sites. Based on these facts, the Institute for Technology and Management in Construction, Department of Deconstruction and Decommissioning of Conventional and Nuclear Buildings, together with the Institute for Photogrammetry and Remote Sensing, is developing an automated drum inspection system as part of the funding measure FORKA – Research for the Deconstruction of Nuclear Facilities. EMOS is a mobile inspection unit that remotely and automatically records the entire surface of the drum, including lid and bottom, optically; evaluates it analytically; and both stores it electronically and outputs the results in the form of an inspection report. In this way, recurring inspections of the drum stock can be completed under the same inspection conditions each time. A decisive advantage is the possibility of carrying out the inspection remotely in order to reduce the radiation dose to the employees on site. The optical evaluation, display and output of the results will ensure a more precise inspection and analysis of the drum surfaces through software to be specially developed than is possible through manual and visual inspections as currently performed in the interim storage facilities. The continuous monitoring of the stored drums will be facilitated and also the tracing of possible damage development through the comparison of archived measurement results is a novel and powerful tool that helps to increase and ensure the safety aspects of interim storage in the long term. Changes in drum geometry as well as in the surface condition (e.g. corrosion formation, etc.) can be identified at an early stage with the help of the inspection unit, and measures can be taken at an early stage to counteract the loss of integrity of the storage containers.

Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network

Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneously generate anomaly alerts and reduce labeling costs. This AOI system works by deploying the GANomaly neural network and the supervised network to the manufacturing system. To improve the ability to distinguish anomaly items from normal items in industry and enhance the overall performance of the manufacturing process, the system uses the structural similarity index (SSIM) as part of the loss function as well as the scoring parameters. Thus, the proposed system will achieve the requirements of smart factories in the future (Industry 4.0).

Defect patterns study of pick-and-place machine using automated optical inspection data

Purpose This paper aims to study the component pick-and-place (P&P) defect patterns for different root causes based on automated optical inspection data and develop a root cause identification model using machine learning. Design/methodology/approach This study conducts experiments to simulate the P&P machine errors including nozzle size and nozzle pick-up position. The component placement qualities with different errors are inspected. This study uses various machine learning methods to develop a root cause identification model based on the inspection result. Findings The experimental results revealed that the wrong nozzle size could increase the mean and the standard deviation of component placement offset and the probability of component drop during the transfer process. Moreover, nozzle pick-up position can affect the rotated component placement offset. These root causes of defects can be traced back using machine learning methods. Practical implications This study provides operators in surface mount technology assembly lines to understand the P&P machine error symptoms. The developed model can trace back the root causes of defects automatically in real line production. Originality/value The findings are expected to lead the regular preventive maintenance to data-driven predictive and reactive maintenance.

Ceramic Cracks Segmentation with Deep Learning

Cracks are pathologies whose appearance in ceramic tiles can cause various damages due to the coating system losing water tightness and impermeability functions. Besides, the detachment of a ceramic plate, exposing the building structure, can still reach people who move around the building. Manual inspection is the most common method for addressing this problem. However, it depends on the knowledge and experience of those who perform the analysis and demands a long time and a high cost to map the entire area. This work focuses on automated optical inspection to find faults in ceramic tiles performing the segmentation of cracks in ceramic images using deep learning to segment these defects. We propose an architecture for segmenting cracks in facades with Deep Learning that includes an image pre-processing step. We also propose the Ceramic Crack Database, a set of images to segment defects in ceramic tiles. The proposed model can adequately identify the crack even when it is close to or within the grout.

A New Approach to Enhance Artificial Intelligence for Robot Picking System Using Auto Picking Point Annotation

Artificial Intelligence (AI) has been widely used in different domains such as self-driving, automated optical inspection, and detection of object locations for the robotic pick and place operations. Although the current results of using AI in the mentioned fields are good, the biggest bottleneck for AI is the need for a vast amount of data and labeling of the corresponding answers for a sufficient training. Evidentially, these efforts still require significant manpower. If the quality of the labelling is unstable, the trained AI model becomes unstable and as consequence, so do the results. To resolve this issue, the auto annotation system is proposed in this paper with methods including (1) highly realistic model generation with real texture, (2) domain randomization algorithm in the simulator to automatically generate abundant and diverse images, and (3) visibility tracking algorithm to calculate the occlusion effect objects cause on each other for different picking strategy labels. From our experiments, we will show 10,000 images can be generated per hour, each having multiple objects and each object being labelled in different classes based on their visibility. Instance segmentation AI models can also be trained with these methods to verify the gaps between performance synthetic data for training and real data for testing, indicating that even at mAP 70 the mean average precision can reach 70%!