This thesis delves into the use of Artificial Intelligence (AI) for quality control in manufacturing systems, with a particular focus on anomaly detection through the analysis of torque measurements in rotating mechanical systems. The research specifically examines the effectiveness of torque measurements in quality control of locks, challenging the traditional method that relies on human tactile sense for detecting mechanical anomalies. This conventional approach, while widely used, has been found to yield inconsistent results and poses physical strain on operators. A key aspect of this study involves conducting experiments on locks using torque measurements to identify mechanical anomalies. This method represents a shift from the subjective and physically demanding practice of manually testing each lock. The research aims to demonstrate that an automated, AI-driven approach can offer more consistent and reliable results, thereby improving overall product quality. The development of a machine learning model for this purpose starts with the collection of training data, a process that can be costly and disruptive to normal workflow. Therefore, this thesis also investigates strategies for predicting and minimizing the sample size used for training. Additionally, it addresses the critical need of trustworthiness in AI systems used for final quality control. The research explores how to utilize machine learning models that are not only effective in detecting anomalies but also offers a level of interpretability, avoiding the pitfalls of black box AI models. Overall, this thesis contributes to advancing automated quality control by exploring the state-of-the-art machine learning algorithms for mechanical fault detection, focusing on sample size prediction and minimization and also model interpretability. To the best of the author’s knowledge, it is the first study that evaluates an AI-driven solution for quality control of mechanical locks, marking an innovation in the field. / Denna avhandling fördjupar sig i användningen av Artificiell Intelligens (AI) för kvalitetskontroll i tillverkningssystem, med särskilt fokus på anomalidetektion genom analys av momentmätningar i roterande mekaniska system. Forskningen undersöker specifikt effektiviteten av momentmätningar för kvalitetskontroll av lås, vilket utmanar den traditionella metoden som förlitar sig på människans taktila sinne för att upptäcka mekaniska anomalier. Denna konventionella metod, som är brett använd, har visat sig ge inkonsekventa resultat och medför fysisk belastning för operatörerna. En nyckelaspekt av denna studie innebär att genomföra experiment på lås med hjälp av momentmätningar för att identifiera mekaniska anomalier. Denna metod representerar en övergång från den subjektiva och fysiskt krävande praxisen att manuellt testa varje lås. Forskningen syftar till att demonstrera att en automatiserad, AI-driven metod kan erbjuda mer konsekventa och tillförlitliga resultat, och därmed förbättra den övergripande produktkvaliteten. Utvecklingen av en maskininlärningsmodell för detta ändamål börjar med insamling av träningsdata, en process som kan vara kostsam och störande för det normala arbetsflödet. Därför undersöker denna avhandling också strategier för att förutsäga och minimera mängden av data som används för träning. Dessutom adresseras det kritiska behovet av tillförlitlighet i AI-system som används för slutlig kvalitetskontroll. Forskningen utforskar hur man kan använda maskininlärningsmodeller som inte bara är effektiva för att upptäcka anomalier, utan också erbjuder en nivå av tolkningsbarhet, för att undvika fallgroparna med svart låda AI-modeller. Sammantaget bidrar denna avhandling till att främja automatiserad kvalitetskontroll genom att utforska de senaste maskininlärningsalgoritmerna för detektion av mekaniska fel, med fokus på prediktion och minimering av mängden träningsdata samt tolkbarheten av modellens beslut. Denna avhandling utgör det första försöket att utvärdera en AI-driven strategi för kvalitetskontroll av mekaniska lås, vilket utgör en nyskapande innovation inom området.

The goal of this investigation was to explore the efficacy of implementing a rehabilitation robot controlled by a noninvasive brain-computer interface (BCI) to influence brain plasticity and facilitate motor learning. The motivation of this project stemmed from the need to address the population of stroke survivors who have few or no options for therapy. A stroke occurs every 40 seconds in the United States and it is the leading cause of long-term disability [1-3]. In a country where the elderly population is growing at an astounding rate, one in six persons above the age of 55 is at risk of having a stroke. Internationally, the rates of strokes and stroke-induced disabilities are comparable to those of the United States [1, 4-6]. Approximately half of all stroke survivors suffer from immediate unilateral paralysis or weakness, 30-60% of which never regain function [1, 6-9]. Many individuals who survive stroke will be forced to seek institutional care or long-term assistance. Clinicians have typically implemented stroke rehabilitative treatment using active training techniques such as constraint induced movement therapy (CIMT) and robotic therapy [10-12]. Such techniques restore motor activity by forcing the movement of weakened limbs. That active engagement of the weakened limb movement stimulates neural pathways and activates the motor cortex, thus inducing brain plasticity and motor learning. Several studies have demonstrated that active training does in fact have an effect on the way the brain restores itself and leads to faster rehabilitation [10, 13-15]. In addition, studies involving mental practice, another form of rehabilitation, have shown that mental imagery directly stimulates the brain, but is not effective unless implemented as a supplemental to active training [16, 17]. Only stroke survivors retaining residual motor ability are able to undergo active rehabilitative training; the current selection of therapies has overlooked the significant population of stroke survivors suffering from severe control loss or complete paralysis [6, 10]. A BCI is a system or device that detects minute changes in brain signals to facilitate communication or control. In this investigation, the BCI was implemented through an electroencephalograph (EEG) device. EEG devices detect electrical brain signals transmitted through the scalp that corresponded with imagined motor activity. Within the BCI, a linear transformation algorithm converted EEG spectral features into control commands for an upper-limb rehabilitative robot, thus implementing a closed-looped feedback-control training system. The concept of the BCI-robot system implemented in this investigation may provide an alternative to current therapies by demonstrating the results of bypassing motor activity using brain signals to facilitate robotic therapy. In this study, 24 able-bodied volunteers were divided into two study groups; one group trained to use sensorimotor rhythms (SMRs) (produced by imagining motor activity) to control the movement of a robot and the other group performed the 'guided-imagery' task of watching the robot move without control. This investigation looked for contrasts between the two groups that showed that the training involved with controlling the BCI-robot system had an effect on brain plasticity and motor learning. To analyze brain plasticity and motor learning, EEG data corresponding to imagined arm movement and motor learning were acquired before, during, and after training. Features extracted from the EEG data consisted of frequencies in the 5-35Hz range, which produced amplitude fluctuations that were measurably significant during reaching. Motor learning data consisted of arm displacement measures (error) produced during an motor adaptation task performed daily by all subjects. The results of the brain plasticity analysis showed persistent reductions in beta activity for subjects in the BCI group. The analysis also showed that subjects in the Non-BCI group had significant reductions in mu activity; however, these results were likely due to the fact that different EEG caps were used in each stage of the study. These results were promising but require further investigation. The motor learning data showed that the BCI group out-performed non-BCI group in all measures of motor learning. These findings were significant because this was the first time a BCI had been applied to a motor learning protocol and the findings suggested that BCI had an influence on the speed at which subjects adapted to a motor learning task. Additional findings suggested that BCI subjects who were in the 40 and over age group had greater decreases in error after the learning phase of motor assessment. These finding suggests that BCI could have positive long term effects on individuals who are more likely to suffer from a stroke and possibly could be beneficial for chronic stroke patients. In addition to exploring the effects of BCI training on brain plasticity and motor learning this investigation sought to detect whether the EEG features produced during guided-imagery could differentiate between reaching direction. While the analysis presented in this project produced classification accuracies no greater than ~77%, it formed the basis of future studies that would incorporate different pattern recognition techniques. The results of this study show the potential for developing new rehabilitation therapies and motor learning protocols that incorporate BCI.