The Internet has revolutionized the way users share and acquire knowledge. As important and popular Web-based applications, online discussion forums provide interactive platforms for users to exchange information and report problems. With the rapid growth of social networks and an ever increasing number of Internet users, online forums have accumulated a huge amount of valuable user-generated data and have accordingly become a major information source for business intelligence. This study focuses specifically on product defects, which are one of the central concerns of manufacturing companies and service providers, and proposes a machine learning method to automatically detect product defects in the context of online forums. To complement the detection of product defects , we also present a product feature extraction method to summarize defect threads and a thread ranking method to search for troubleshooting solutions. To this end, we collected different data sets to test these methods experimentally and the results of the tests show that our methods are very promising: in fact, in most cases, they outperformed the current state-of-the-art methods. / Ph. D.

Computer vision, a prominent subfield of artificial intelligence, has gained widespread util-ization in diverse domains such as surveillance, security, and robotics. This research en-deavors to develop an semi-automated defect detection system serving as a quality controlassurance mechanism for Nolato MediTor, a manufacturing company within the medicaldevice industries engaged in the production of anesthesia breathing bags. The primary fo-cus of this study revolves around the detection of a specific defect, namely, holes. Withinthe context of Nolato MediTor, prioritizing recall (sensitivity) assumes utmost signific-ance as it entails favoring the rejection of functional breathing bags over the inadvertentacceptance of defective ones. The proposed system encompasses a robust metallic standfacilitating precise positioning for three distinct camera angles, accompanied by a XiaomiRedmi Note 11 Pro phone and a software component, designed to process incoming imagefolders representing a complete view of a breathing bag from multiple angles. Subsequently,these images undergo analysis using the learned weights derived from the implementedMask R-CNN model, enabling a cohesive assessment of the breathing bag. The system’sperformance was rigorously evaluated, and the best-performing weights demonstrated aremarkable recall rate of 0.995 for the first test set, exceeding the desired recall thresholdof 95%. Similarly, for the second test set, the recall rate achieved an impressive value of0.949, narrowly missing the 95% threshold by a marginal 0.001. Furthermore, the com-putational efficiency, quantified as the processing time per breathing bag, on average, thelongest duration recorded amounted to approximately 10.151 seconds, with the poten-tial for further enhancement by employing a higher standard GPU. This study serves as aproof of concept, demonstrating the feasibility of achieving semi-automated quality controlutilizing CNN. The implemented system represents a promising prototype with potentialscalability for improved operational conditions and expanded defect coverage, thus pavingthe way towards a fully automated quality control within large-scale industries.

Software testing is essential for quality assurance, with automated techniques such as random testing and adaptive random testing being cost-effective solutions compared to others. Adaptive random testing seeks to enhance random testing, and there is a conception that adaptive random testing always should replace random testing. Our research question investigates this conception by addressing a gap in the literature, where a comparison between the two techniques in terms of certain key metrics is missing, namely defect detection efficiency and test case generation time. Defect detection efficiency is the amount of defects detected divided by the number defects in the system multiplied by one hundred. Test case generation time is the time it takes to generate all of the test case inputs. These metrics where chosen as they can be seen as a measurement of the techniques effectiveness and efficiency respectively. In order to address this research question we employ a quantitative experiment where we compare the performance of random testing and adaptive random testing with a sole focus on these two metrics. The comparison is performed by implementing and testing both algorithms on eight error-seeded numerical programs and measuring the results. The results displayed that adaptive random testing had a defect detection efficiency total average of 21.59% and a test case generation time total average of 35.37 (ms), while random testing had a defect detection efficiency total average of 22.28% and a test case generation time total average of 0.26 (ms). These results might contribute to disproving the conception that adaptive random testing always should replace random testing, as random testing evidently performed better on both the measured metrics.

No description available.

Laser powder bed fusion (LPBF) remains a predominately open-loop additive manufacturing process with minimal in-situ quality and process control. Some machines feature optical monitoring systems but lack automated analytical capabilities for real-time defect detection. Recent advances in machine learning (ML) and convolutional neural networks (CNN) present compelling solutions to analyze images in real-time and to develop in-situ monitoring. Approximately 30,000 selective laser melting (SLM) build images from 31 previous builds are gathered and labeled as either “okay” or “defect”. Then, 14 open-sourced CNN were trained using transfer learning to classify the SLM build images. These models were evaluated by F1 score and down selected to the top 3 models. The top 3 models were then retrained and evaluated using Dietterich’s 5x2 cross-validation and compared with pairwise student t-tests. The pairwise t-test results show no statistically significant difference in performance between VGG- 19, Xception, and InceptionResNet. All models are strong candidates for future development and refinement. Additional work addresses the entire model development process and establishes a foundation for future work. Collaborations with computer science students has produced an image pre-processing program to enhance as-taken SLM images. Other outcomes include initial work to overlay CAD layer images and preliminary hardware integration plan for the SLM machine. The results from this work have demonstrated the potential of an optical layer-wise image defect detection system when paired with a CNN.

Early detection of rail defects is necessary for preventing derailments and costly damage to the train and railway infrastructure. A rail surface flaw can quickly propagate from a small fracture to a broken rail after only a few train cars have passed over it. Rail defect detection is typically performed by using an instrumented car or a separate railway monitoring vehicle. Rail surface irregularities can be measured using accelerometers mounted to the bogie side frames or wheel axles. Typical signal processing algorithms for detecting defects within a vertical acceleration signal use a simple thresholding routine that considers only the amplitude of the signal. As a result, rail surface defects that produce low amplitude acceleration signatures may not be detected, and special track components that produce high amplitude acceleration signatures may be flagged as defects. The focus of this research is to develop an intelligent signal processing algorithm capable of detecting and classifying various rail surface irregularities, including defects and special track components. Three algorithms are proposed and validated using data collected from an instrumented freight car. For the first two algorithms, one uses a windowed Fourier Transform while the other uses the Wavelet Transform for feature extraction. Both of these algorithms use an artificial neural network for feature classification. The third algorithm uses the Wavelet Transform to perform a regularity analysis on the signal. The algorithms are validated with the collected data and shown to out-perform the threshold-based algorithm for the same data set. Proper training of the defect detection algorithm requires a large data set consisting of operating conditions and physical parameters. To generate this training data, a dynamic wheel-rail interaction model was developed that relates defect geometry to the side frame vertical acceleration signature. The model was generated by using combined systems dynamic modeling, and the system was solved with a developed combined lumped and distributed parameter system numerical approximation. The broken rail model was validated with real data collected from an instrumented freight car. The model was then used to train and validate the defect detection methodologies for various train and rail physical parameters and operating conditions. / Ph. D.

Defected wheel are one the major reasons endangered state of railroad vehicles safety statue, due to vehicle derailment and worsen the quality of freight and passenger transportation. Therefore, timely defect detection for monitoring and detecting the state of defects is highly critical. This thesis presents a passive non-contact acoustic structural health monitoring approach using ultrasonic acoustic emissions (UAE) to detect certain defects on different structures, as well as, classifying the type of the defect on them. The acoustic emission signals used in this study are in the ultrasonic range (18-120 kHz), which is significantly higher than the majority of the research in this area thus far. For the proposed method, an impulse excitation, such as a hammer strike, is applied to the structure. In addition, ultrasound techniques have higher sensitivity to both surface and subsurface defects, which make the defect detection more accurate. Three structures considered for this study are: 1) a longitudinal beam, 2) a lifting weight, 3) an actual rail-wheel. A longitudinal beam was used at the first step for a better understanding of physics of the ultrasound propagation from the defect, as well, develop a method for extracting the signature response of the defect. Besides, the inherent directionality of the ultrasound microphone increases the signal to noise ratio (SNR) and could be useful in the noisy areas. Next, by considering the ultimate goal of the project, lifting weight was chosen, due to its similarity to the ultimate goal of this project that is a rail-wheel. A detection method and metric were developed by using the lifting weight and two type of synthetic defects were classified on this structure. Also, by using same extracted features, the same types of defects were detected and classified on an actual rail-wheel. / Master of Science

Software testing is important, but judging whether a set of software tests is effective is difficult. This problem also appears in the classroom as educators more frequently include software testing activities in programming assignments. The most common measures used to assess student-written software tests are coverage criteria—tracking how much of the student’s code (in terms of statements, or branches) is exercised by the corresponding tests. However, coverage criteria have limitations and sometimes overestimate the true quality of the tests. This dissertation investigates alternative measures of test quality based on how many defects the tests can detect either from code written by other students—all-pairs execution—or from artificially injected changes—mutation analysis. We also investigate a new potential measure called checked code coverage that calculates coverage from the dynamic backward slices of test oracles, i.e. all statements that contribute to the checked result of any test. Adoption of these alternative approaches in automated classroom grading systems require overcoming a number of technical challenges. This research addresses these challenges and experimentally compares different methods in terms of how well they predict defect-detection capabilities of student-written tests when run against over 36,500 known, authentic, human-written errors. For data collection, we use CS2 assignments and evaluate students’ tests with 10 different measures—all-pairs execution, mutation testing with four different sets of mutation operators, checked code coverage, and four coverage criteria. Experimental results encompassing 1,971,073 test runs show that all-pairs execution is the most accurate predictor of the underlying defect-detection capability of a test suite. The second best predictor is mutation analysis with the statement deletion operator. Further, no strong correlation was found between defect-detection capability and coverage measures. / Ph. D.

Over the past few decades, additive manufacturing (AM) or 3D printing (3DP) technologies witnessed revolutionary growth in the manufacturing sector. Parts produced with metal AM techniques, especially Laser Powder Bed Fusion (LPBF), are often prone to porosity issues. The presence of pores leads to harmful effects such as crack formation and, eventually, premature failure of the component. Consequently, research in defect detection and pore prediction attracted substantial attention. Utilizing image-based porosity detection in preexisting systems is a simple, effective, and cost-efficient approach for final part inspection. This thesis investigates the possibility of predicting porosity using U-Net and its novel network architectures named RU-Net and RAU-Net, on an X-ray computed tomography (XCT) image dataset. Later, the performance of these models is analyzed and compared using precision, recall, F1 score, mAP, IoU metrics, and their hybrid losses combining BCG and Dice loss. RAU-Net outperforms RU-Net and U-Net in all these metrics by detecting more than 90% of actual pores while retaining 95% precision. While RU-Net and U-Net required additional training, RAU-Net achieved high performance in only 50 epochs, demonstrating its data efficiency and convergence. Due to its shorter training period, also leading to lower computational overhead, RAU-Net is suited for practical high throughput and low latency applications. Particularly in time-sensitive applications, RAU-Net can enable more widespread adoption of dense prediction networks. A custom script is developed for estimating the porosity percentage level in 3D printed metal components precisely, further enhancing final product inspection procedures. As a result, the entire quality control process is simplified, which allows for the quicker inspection of final components to deliver, by ensuring they meet required quality and reliability standards.

<p dir="ltr">The study builds and evaluates three advanced neural network models—ResNet-34, EfficientNet B0, and SqueezeNet—for defect detection and classification of silicon wafer map images. The study evaluates the neural network model in two cases, binary and multi-class classifications. The binary classification, which is crucial for promptly determining whether a wafer map is defective, EfficientNet-B0 led with the highest test accuracy of 94.62% and an average accuracy of 93.2%. Similarly, in multi-class classification, necessary for pinpointing specific defect causes early in the manufacturing process, EfficientNet-B0 achieved the top test accuracy of 84.22% with an average accuracy of 84.07%. Further enhancements in the study resulted from strategic pruning of EfficientNet-B0, specifically the removal of Residual Block 2 after convolutional layer visualization revealed minimal impact on accuracy, with a reduction of just 1.33%. These modifications not only refined the learning process but also reduced the model size by 33%, thereby increasing computational efficiency. The integration of Grad-CAM++ visualizations ensured the model focused on pertinent features, thus boosting the transparency and reliability of the defect detection process. The results underscore the potential of advanced neural networks to significantly enhance the accuracy and efficiency of semiconductor manufacturing.</p>