02. Master's Thesis

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 20 of 505
  • ItemOpen Access
    THE EFFECTIVENESS OF MACHINE LEARNING IN CONSTRUCTION AND DEMOLITION WASTE RECOGNITION FROM SATELLITE IMAGES IN ASTANA
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-08-06) Iliyas, Kazbek
    In rapidly urbanizing areas like Astana city, identifying and managing construction and demolition waste (CDW) is becoming more and more difficult. The growing volume and complexity of CDW are excessive for traditional waste management techniques to handle, which results in operational and environmental inefficiencies. To solve the issue, this thesis assesses how well machine learning techniques work in identifying CDW in these cities from satellite images. Accurate detection can greatly help with the management of waste, which is essential for maintaining the health of urban environments. The model was trained with state-of-the-art object recognition and segmentation techniques, resulting in a mean intersection over union (IoU) of 0.380. Although this performance is below the benchmark norms (0.457 to 0.56), as reported in similar research, it still shows great potential. 200 photos were gathered and annotated as part of the process, which was then used to train and validate the model. Key findings include the effect of image quality on detection accuracy and notable differences in performance across various waste types. The model showed an accuracy of 0.80 for both training and validation; however, recall (2.12%) and precision (3.22%) still need to be improved. Some misclassifications were observed during visual inspection since CDW and non-waste materials had similar appearances. To improve detection accuracy, we suggest that future studies look into more sophisticated data augmentation methods and effective model architectures. The use of Google Earth imagery and a simplified two-class classification scheme are two of the study's limitations. These drawbacks imply that to fully reflect the complexity of CDW detection, future research should take multi-class classification into account and include a wider range of data sources. Our findings contribute to the field of environmental monitoring by demonstrating both the potential and challenges of applying machine learning to urban waste management.
  • ItemOpen Access
    APPLICATION OF BUILDING INFORMATION MODELLING (BIM) FOR SAFETY MANAGEMENT (SM) DURING THE OPERATION AND MAINTENANCE (O&M) PHASE IN BUILDINGS IN KAZAKHSTAN
    (Nazarbayev University School of Engineering and Digital Sciences, 2022) Kopeyev, Dastan
    Safety management is one of the key concerns of the construction objects industry. Building information modeling enables the creation of a digital built environment of the building. It could also be applied for early safety issues identification and safety management throughout the construction project lifecycle. Currently, BIM usage for building O&M phase safety still has little attention. There are different studies evaluating its general efficiency in early safety risks identification and usage of the BIM model for safety management during building operation and maintenance. Kazakhstan is currently in the important stage of BIM adoption, but no studies observe BIM application for Kazakhstani building O&M safety.
  • ItemOpen Access
    Numerical modeling for seismic microzonation in Singapore
    (Nazarbayev University School of Engineering and Digital Sciences, 2022) Abdialim, Shynggys
  • ItemOpen Access
    ENGINEERING PROPERTIES OF CEMENT-TREATED SILTY SAND SUBJECTED TO FREEZE THAW CYCLES
    (Nazarbayev University School of Engineering and Digital Sciences, 2022) Sagidullina, Nazerke
    The problem of soft ground is currently of great interest, as with the rapid development of infrastructure, researchers are trying to cope with the improvement of properties of problematic soil to build structures on it since any structures built on weak soils can be easily damaged. In cold regions, the problem of weak soils is further exacerbated by freeze-thaw cycling, resulting in reduced soil strength. For the improvement of soil properties, the soil stabilization method can be used. For such purposes, ordinary Portland Cement (OPC) is commonly used. However, despite the effectiveness of OPC cement as a binding material, it produces a significant amount of carbon dioxide emission. As an alternative to OPC, calcium sulfoaluminate (CSA) cement can be used. Therefore, the purpose of this research study is to present the results from laboratory experiments to evaluate the effectiveness of the soil treatment method using CSA cement for the improvement of the properties of silty sand. The unconfined compressive strength (UCS) and ultrasonic pulse velocity (UPV) testing conducted on the soil samples that were cured for 3, 7, and 14 days and subjected to 0, 1, 3, 5, 7, 10, and 15 freeze-thaw cycles. The water content is defined from the optimum moisture content and three different cement content were used, 3%, 5%, and 7%. Applying the results from the unconfined compressive strength (UCS) test, the strength loss/gain and resilient modulus parameters were obtained. The findings of the study show that the strength and pulse velocity values decreased with the exposure of soil specimens to cyclic freezing and thawing. However, improvement in soil performance can be observed with the use of CSA cement. Overall, the application of CSA cement for treatment purposes could be an effective method to enhance soil performance and meet the subgrade design requirements.
  • ItemOpen Access
    Performance optimization and reliability improvement of railroad signaling in Kazakhstan with FPGAs
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-09) Kabi, Sultan
    In this study the software implementation of a simulation of the railroad station and optimal pathfinding between two points(segments) was modeled for the railroad systems. The prototype processing unit will be created and evaluated on a FPGA equipment, and Java algorithm specifically designed for efficient hardware implementation and simulation of the track design. The autonomous system uses a linear approach to manage the system, considering inputs that include the train's current states, segment’s current state(track, junctions etc.), coordinates and type. This system, which is linked to each individual train controller, determines the best option for all operating locomotives by sending data to the Java application that simulates the railway layout(design) and showing real-time position of the train. Sensors that are positioned at different points on the rails serve as the inputs, while the switches which regulate the pathway serve as its output. Remote transferof data is a crucial resource for a firm that requires immediate access to information as a factor of strategy in making choices. Monitoring specific characteristics in train industry might assist avoiding incidents and enhance customer services.
  • ItemRestricted
    Advanced Circuit Configurations for RF Wireless Power Transfer
    (Nazarbayev University School of Engineering and Digital Sciences, 2024) Azhmuratov, Serik
  • ItemRestricted
    MICROWAVE KINETIC INDUCTANCE DETECTOR SIGNAL DENOISING USING MACHINE LEARNING
    (Nazarbayev University School of Engineering and Digital Sciences, 2024) Maksut, Zhansaya
    Superconducting micro-resonators are crucial in creating superposition states in quan tum computers and are gaining prominence as quantum technology evolves. Beyond their quantum applications, these resonators are instrumental as ultra-sensitive de tectors in astronomy, particularly Microwave Kinetic Inductance Detectors (MKIDs), which are key for both scientific exploration and industrial use. However, the is sue of electronic noise in these detectors remains a significant hurdle. To address this, our approach integrates machine learning strategies alongside conventional noise reduction methods to improve MKID signal fidelity. Our process involves gathering data and applying denoising models, with a strong emphasis on machine learning techniques. Our findings highlight the strengths of dif ferent denoising techniques, particularly deep learning architectures like Long Short Term Memory (LSTM) networks and Autoencoders, which demonstrate promising results in denoising MKID signals. These models exhibit adaptability to diverse noise sources, proficiency in identifying complex noise patterns, and continuous improve ment with additional data. This research represents a significant advancement in the field and provides es sential insights into improving MKID detectors, which in turn could lead to ground breaking developments in various scientific areas.
  • ItemEmbargo
    ANALYSIS OF EFFICIENT REGIONS FOR WIND POWER GENERATION IN KAZAKHSTAN
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-05) Aryngazin, Anuar
    Global concerns about climate change and the decreasing of fossil fuels reserves have made renewable energy production a major priority. Wind energy is a well-established research area. However, identifying optimal regions for wind power production requires weighing multiple factors, including wind speed, density, availability, and the environmental consequence of reducing greenhouse gas (GHG) productions, and application of decision analysis. The main purpose of this study is to analyze the regions of Kazakhstan and identify the optimal location for wind energy production using the decision analysis extension of multiattribute utility theory (MAUT). Previous literature conducted analyzing wind power potential in Kazakhstan has identified several promising locations for efficient wind energy production. However, the selection process did not involve mathematical analysis; instead, the choice was primarily determined by quantitative results obtained from empirical studies. This study identified seven favorable areas based on expected utility and a comprehensive study was conducted using the multiattribute utility function (MUF). This method facilitated the selection of wind energy projects in efficient regions, taking into account factors such as potential power production and GHG emission reduction potential. The study involves collecting data on the GHG emission reduction potential and wind speed, followed by analysis and decision making to identify practical wind energy projects. Moreover, the data analysis includes a questionnaire for the decision maker (DM). This made it possible to determine the optimal locations for installing wind farms based on the real preferences of an expert in the field of energy. The results based on the expected utility values showed that the most optimal location for installing a wind power plant is Fort-Shevchenko and Yereymentau. The results of the research project are critical for the development of wind energy in Kazakhstan and for identifying the most efficient regions for wind energy production using utility theory. This study contributes to the development of wind energy in Kazakhstan and provides information for decision-making processes on sustainable energy production.
  • ItemRestricted
    PARAMETER IDENTIFICATION OF A MODEL PLANE FROM WIND TUNNEL DATA
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04) Bashkenov, Samat
    The study examines parameter identification and identifiability of aircraft model parameters using a wind tunnel. Initially, a second-order canonical equation was used to perform identifiability and parameter identification tests in Simulink and MATLAB. In this simulation part, three different input signals, step, pulse, and 3211 are applied. The results of the identifiability tests for all three types of input signals showed which parameter can be determined. Next, the transfer function and least squares methods were used to identify the parameters in the MATLAB/Simulink program, which determined the exact values of the parameters. A one degree of freedom aircraft model is tested in a wind tunnel in longitudinal pitching motion. The aim is to conduct an identifiability test and perform parameter identification using the transfer function method with MATLAB/Simulink. Step and 3211 input types were used. The identifiability test showed that the aerodynamic moment derivative with respect to angle of attack (𝑀 ) has the highest sensitivity, which means it has the highest α accuracy. Also, sensitivity analysis obtained that other values are within same order of magnitude, hence the evaluation is possible for these parameters. It means that these parameters can be identified, but with different accuracy. The parameter identification was conducted successfully utilizing step and 3211 input signals. It can be highlighted that the result was more accurate using 3211 input signal. The study effectively identified the parameter of the aircraft model using theoretical calculations, testing, and sensitivity analysis.
  • ItemOpen Access
    UNDERWATER WIRELESS POWER TRANSFER MODELLING AND SIMULATION (STUDY ON FOREIGN METAL OBJECTS)
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04) Toibekkyzy, Aidana
    For a long time, the Autonomous Underwater Vehicle (AUV) has played a vital role in deepsea investigations and the exploration of ocean resources. However, the primary concern related to underwater vehicles is the lack of sufficient battery capacity to sustain their numerous high-power sensors and their durable autonomous activities under the sea. In comparison with the traditional methods of powering AUVs, the Wireless Power Transfer (WPT) systems ensure the transfer of electricity without any usage of cables or wires. It ensures a prolonged mission duration and mobility of AUV, increasing its performance. Eliminating the plugging-in and -out procedures, the WPT technology provides a safe and practical solution for powering AUVs. However, there are a number of factors of the seawater medium that cannot be manually controlled. Such considerations make it complex to model a system able to transfer power with adequate efficiency. Therefore, this thesis analyzes an underwater WPT system and investigates its behavior under different conditions of the surrounding environment. It provides a quantitative analysis of the influence of the environment, external objects, and misalignment between the resonators on the electrical properties of the coil and the performance of the underwater WPT system. This is performed by testing the WPT in different media, namely in air, seawater, and more conductive water; testing in the presence of objects with different material types, sizes, thicknesses, and shapes; as well as testing the model when coils are not perfectly aligned. The results suggest that the conductive environment causes more eddy current generation, decreasing the efficiency of WPT. The placement of foreign objects differently affects the system, depending on the induced eddy currents on them, the magnetization effect, and how localized the magnetic field is around the coil.
  • ItemEmbargo
    STRUCTURAL AND MORPHOLOGICAL PROPERTIES OF COLLAGENS IN RABBIT MENISCUS
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-07) Yeralimova, Kamila
    The meniscus in the knee plays an important role in the proper functioning of the knee joint and the maintenance of its health. It protects the femur and tibia from wearing, lubricates, and provides nutrients and oxygen for the tissues in the knee joint. The meniscus cannot heal spontaneously due to its low vascularization and continuous deformation. Therefore, severe meniscus tears remain a significant clinical challenge. The most common method of treatment is to remove the damaged part of the tissue, however, since this procedure removes a layer of protection between the femur and tibia bones, the friction created by the continuous movement of the joint components damages the articular cartilage and, as a result, leads to osteoarthritis (OA). Accordingly, alternative strategies, including tissue engineering (TE), are needed to overcome the clinical challenge. In TE-based approaches, a scaffold that mimics the properties of the native tissue structure is essential for the cells to reside and synthesize the tissue components, simultaneously serving as a support material. The design and fabrication of such a scaffold require knowledge about the properties of the native tissue, including the structural organization of the components. In this study, the meniscus tissues harvested from rabbits were characterized in terms of collagen fiber diameter distribution, cellular organization and modulus. The findings revealed that the collagen fibril diameter ranged from 50 nm to 170 nm and from 30 nm to 130 nm for medial and lateral meniscus, respectively. Average fibril diameters for medial and lateral regions of the meniscus were found as 91.41.±26.7 and 50.86±19.1, respectively. The histology images demonstrated that the cells were evenly distributed over the entire tissue. In the upper part of the meniscus, the compressive moduli measured in the top region, middle region, and bottom region were determined to be 0.019±0.03, 0.00015±0.0001, and 0.0006±0.00019 MPa, respectively. In the lower part of the meniscus, the compressive moduli measured in the top region, middle region, and bottom region were determined to be 2.19±1.5, 1.22±0.37, and 1.08±0.66 MPa. The findings of this can provide significant input for the design and fabrication of biomaterial scaffolds for meniscus repair and regeneration.
  • ItemEmbargo
    THE DESIGN OF SELF-CHARGING SENSOR INDUCED SIMPLIFIED INSOLE-BASED PROTOTYPES WITH PRESSURE MEASUREMENT FOR FAST SCREENING OF FLAT-FOOT
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-05) Anash, Adeliya; Oralkhan, Sabyrzhan; Issabek, Moldir; Nuriya, Nurbergenova
    Flatfoot is an orthopedic foot malformation in which the inner arch of the foot virtually or completely flattens during static or dynamic motions. This abnormal deformation can negatively affect the musculoskeletal system, leading to chronic pains and other conditions that may severely deteriorate a person’s quality of life if not treated timely. Therefore, there is a need for continuous monitoring of food conditions, and currently, available screening methods may not be sustainable in terms of objectivity, time, and money. This research aims to design and fabricate an insole-based screening device that would offer accurate and accessible screening. In order to implement our objectives, the self-powered triboelectric nanogenerators (TENG) were used as tactile pressure sensors for the insole since they propose such advantages as uncomplicated fabrication and design operations, cost-effectiveness, extensive lifetime, and high output power. TENGs’ main purpose is converting mechanical energy into electrical energy. In other words, the energy generated from the movement of the object is translated into electric output and recorded by the Arduino circuits. The collected data is analyzed using machine learning algorithms for the system to be able to immediately recognize the flatfoot conditions after undergoing the training sessions. To collect data, 82 participants were asked to march in one place and walk the same amount of time and distance to get similar numbers of outputs from each operation. The analysis showed that the middle sensors of the insoles generated much higher electricity when they were attached to people with flatfoot conditions and that they exhibited relatively uniform equal pressure distribution throughout the foot. In contrast, people with normal feet put more pressure on the front and back side of the foot. The overall accuracy of the machine learning system reached 81%, indicating that the designed insole has a high potential to be used as a flatfoot detecting device commercially.
  • ItemRestricted
    AIR-TO-GROUND CHANNEL MODELING FOR UNMANNED AERIAL VEHICLES
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04-19) Mukhatzhanova, Sabina
    The ‘Air-to-Ground Channel Modeling for Unmanned Aerial Vehicles’ main goal is to develop a precise and reliable model of the communication channel between unmanned aerial vehicles and ground stations. This project will be mainly focused on the extensive research of recent data and channel simulation using MATLAB. The project will analyze different scenarios and characteristics that may have an impact on the proper work of the channel and find ways to overcome those difficulties. These obstacles can be channel fading, polarization, weather conditions, and hard-to-reach locations. The proposed channel modeling can be beneficial in different spheres of life: safety, surveillance, telecommunication, and national priorities. Overall, the project’s main focus will be based on the enhancement of analytical skills in order to select major types of channel modeling and see the advantages and disadvantages of the proposed model. The results can have a positive impact through the contribution to the advancement of UAV technologies.
  • ItemEmbargo
    COMPUTATIONAL FLUID DYNAMICS IN PANCREATICOBILIARY JUNCTION
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04) Turgaliyev, Alim
    Pancreaticobiliary maljunction without biliary dilation is associated with pancreaticobiliary reflux, a pathophysiologic factor underlying a wide range of diseases, including gallbladder cancer. This work used computational flow simulations to examine the mechanisms and relevant geometric features that influence pancreaticobiliary reflux and assess the impact of surgical interventions. The results suggest that the refilling phase is the primary mechanism driving pancreaticobiliary reflux. Moreover, the cystic duct diameter was the most critical factor determining the reflux dynamics. Furthermore, the configuration of the baffle system (the baffle height ratio and the number of baffles) affected the dynamics of pancreaticobiliary reflux. Also, the study underscores the potential therapeutic efficacy of cholecystectomy and endoscopic retrograde cholangiopancreatography in managing pancreaticobiliary reflux in cases of pancreaticobiliary maljunction without biliary dilatation. These interventions offer promising avenues for reducing reflux-related complications and mitigating the progression of associated diseases.
  • ItemOpen Access
    TOWARDS MORE RELIABLE DRUG TOXICITY PREDICTION: AN ENSEMBLE APPROACH
    (Nazarbayev University School of Engineering and Digital Sciences, 2024) Yarovenko, Vladislav
    The development of a single pharmaceutical drug is a time- and resource-consuming process with a high likelihood of rejection. In recent years, the cost-effectiveness of a single drug has decreased drastically, as the criteria for passing has become more rigorous. A huge fraction of attrition rates is caused by the toxicity of chemical compounds. Recent findings in Machine Learning (ML) have revolutionized the drug toxicity prediction field, developing many model architectures and data representations. The faced challenges are different ways of representing the molecules’ chemical structure, as well as many different toxicity types. This study proposes a novel drug toxicity prediction framework. It uses several classification models, based on different data representations and different ways of combining their features. The evaluation of six different datasets with different toxicity types shows that choosing majority voting across all models can improve the ROC AUC score and accuracy. Using a single classification model to combine these datasets demonstrates that it is possible to achieve 84% accuracy on data with various toxicity types. The findings of this research provide insights into the application of ML in pharmaceutical research. Improving current methods of toxicity assessment can have a positive effect on the efficiency and cost-effectiveness of drug development.
  • ItemRestricted
    ENHANCING EMERGENCY RESPONSE: THE ROLE OF INTEGRATED VISION-LANGUAGE MODELS IN IN-HOME HEALTHCARE AND EFFICIENT MULTIMEDIA RETRIEVAL
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-06) Abdrakhmanov, Rakhat
    Incidents of in-home injuries and sudden critical health conditions are relatively common and necessitate swift medical expertise. This study introduces an innovative use of vision-language models (VLMs) to elevate human healthcare through improved emergency recognition and efficient multimedia search capabilities. By harnessing the combined strengths of large language models (LLMs) and vision transformers (ViTs), this study enhances the analysis of both visual and textual information. We propose a framework that utilizes the PrismerZ VLM in both its Base and Large forms, along with a key frame selection (KFS) algorithm, to pinpoint and exam- ine pertinent images within video streams. This allows for the creation of enriched datasets, filled with images that are paired with descriptive narratives and insights gained from visual question answering (VQA). Through the integration of the CLIP- ViT-L-14 model and the MongoDB Atlas cloud database, we developed a multimodal retrieval system that achieves complex query handling and improved user experience. Additionally, this research undertakes data collection to assess the system’s adaptabil- ity, providing proof of concept and refining the framework. The results showcase the system’s robustness, evidenced by high accuracy rates—86.5% in image captioning and 92.5% in VQA tasks—on the kinetics dataset. When tested with human subject data, the PrismerZ Large model achieved 85.8% accuracy in image captioning and 87.5% in VQA tasks. This performance was further enhanced through fine-tuning with the GPT-4 based Chat GPT, one of the largest language assistants, leading to a 20% improvement in semantic text similarity as measured by the BERT model. The PrismerZ models also stand out for their speed, with the Base and Large versions processing image captioning and VQA tasks in just seconds, even on the NVidia Jet- son Orin NX edge device. These findings confirm the system’s reliability in real-life scenarios. The multimodal retrieval system achieved top performance with a mean average precision at k (MAP@k) of 93% and mean reciprocal rank (MRR) of 94.79% on the kinetics dataset, maintaining an average search latency of merely 0.33 seconds for text queries. This research significantly propels the fields of human activity recognition (HAR) and emergency detection forward, carving out new paths for anomaly detection and enriched multimedia understanding. Our objective in integrating the VLM with multimedia information retrieval is to establish new benchmarks for hu- man care, improving its timeliness, comprehensiveness, and efficiency in accessing multimedia data
  • ItemRestricted
    PREDICTING SOLAR FLARE OCCURRENCES USING TIME-SERIES DATA FROM NASA’S API FOR SPACE WEATHER FORECASTING
    (Nazarbayev University School of Engineering and Digital Sciences, 2024) Seit, Damir
    This thesis investigates the complicated area of solar flare and Coronal Mass Ejection (CME) prediction using data science approaches and NASA’s Application Programming Interface (API) for the purpose of comparing time-series prediction models in terms of accuracy and interpretability. Quick, intense solar eruptions labeled as CMEs and solar flares have significant impacts on space weather and Earth’s technological systems. The data for this research is taken from the open NASA API service. To understand the underlying relationships governing these solar events, we utilize both state-of-the-art LSTM and well-known models such as Autoregressive Integrated Moving Average (ARIMA), Linear Regression, and Autoregressive (AR) model. The dataset was gathered using a specifically developed Python application with the help of RESTful API. A key part of our research is the dual assessment of these models, which evaluates in terms of both forecast accuracy and interpretability. The interpretability of the tested models is measured using the SOC (simulatability operations count) score metric, which counts the number of arithmetic operations performed to predict a single test case. This study shows that simpler approaches in univariate time-series forecasting perform better than more complex ones in terms of accuracy and interpretability with small dataset. However, only Linear Regression made a reasonable predictions of extreme peak events.
  • ItemRestricted
    ASSESSMENT OF MICROPLASMA SPRAYING OF BIOACTIVE COATINGS ON TITANIUM IMPLANTS FOR BIOCOMPATIBILITY IN VITRO
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04) Nwachukwu, China Jesse
    This study presents an assessment of microplasma spraying (MPS) as a technique for applying bioactive coatings on titanium implants to enhance biocompatibility in vitro. The research aims to evaluate the effectiveness of MPS in promoting osteogenic differentiation and antimicrobial activity of titanium implants through in vitro assays. Surface-modified titanium implants with zirconium, hydroxyapatite, tantalum, and titanium coatings of varying roughness were fabricated using MPS. Osteogenic differentiation potential was assessed via alkaline phosphatase (ALP) activity and alizarin red staining, revealing significant variations in mineralization among the different coatings. Antimicrobial studies utilizing Escherichia coli as a model organism demonstrated differential growth kinetics in the presence of implant material extracts, suggesting potential antimicrobial properties associated with specific coatings. The results underscore the importance of surface modifications in influencing osteogenic differentiation and antimicrobial activity of titanium implants. Zirconium, hydroxyapatite, and tantalum coatings exhibited distinct mineralization patterns and antimicrobial effects compared to uncoated titanium, highlighting the potential of MPS in enhancing the biocompatibility of titanium implants. These findings contribute to the understanding of surface engineering techniques for implant materials and pave the way for further research aimed at optimizing coating formulations and deposition parameters to improve implant performance and clinical outcomes
  • ItemRestricted
    PHOTOTOUCH: SOFTWARE AND HARDWARE METHODS FOR PHOTOELASTIC TACTILE SENSOR
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04) Zhuzbay, Nurdaulet
    This thesis introduces a novel approach for predicting force at the fingertips of tendon driven robotic fingers using the photoelastic effect. The core of this technique lies in the detection of stress-induced birefringence in silicone, which becomes visible as distinctive fringe patterns under polarized light. These patterns emerge when tendons, embedded within a silicone matrix, apply forces that compress the material. They are not merely visual markers, but also contain valuable data about the applied forces and their distribution within the silicone. To extract and utilize this data effectively, Convolutional Neural Network (CNN) was employed, specially designed to analyze and interpret the intricate fringe patterns. Thousands of these images were captured in various force application states, resulting in a substantial dataset for the CNN to learn from. The finger was used to show the position control and force control capabilities of photoealastic tactile sensor. It was successful in following the sine wave during force control mode, with RMSE of 0.59 N at a frequency of 0.05 Hz. This document will further delve into relevant literature, elaborate on the research methodology, describe the experimental setup, and present preliminary findings. Col lectively, these components unveil the immense potential of the proposed system in augmenting the tactile capabilities of robotic appendages, with far-reaching implica tions for the fields of robotics and automated systems.
  • ItemRestricted
    FIBER OPTIC SHAPE SENSORS FOR DEVICES
    (Nazarbayev University School of Engineering and Digital Sciences, 2024-04) Karzhaubayeva, Dana
    The usage of fiber optics for sensing purposes become popular in recent years due to its advantages such as compatibility, flexibility, and high sensitivity. The literature review observed different types of fiber optics sensors, their applications, and strengths and weaknesses. The setup, which provides real-time shape and temperature sensing, was constructed during this study. The purpose of this work is to conduct laboratory experiments to design a setup that will sense strain and temperature values by fiber optical fibers in real time. Insertion into phantom results illustrate how the shape of the inserted needle changes through different layers of it. Radiofrequency thermal ablation experiment results demonstrate how the temperature was sensed by fibers based on their positions in a heated phantom.