Gearbox fault detection plays a crucial role in ensuring the reliable operation of machinery and preventing costly downtime. This research thesis aims to develop and evaluate ensemble learning techniques for accurate detection of gearbox broken tooth conditions using vibration data from SpectraQuest's Gearbox Fault Diagnostics Simulator. The dataset comprises vibration readings from sensors under both healthy and broken tooth conditions. A thorough analysis of the Gearbox Fault Diagnosis Dataset was conducted, integrating time and frequency domain analyses to inform feature engineering. A comprehensive comparative analysis of bagging, boosting, stacking, and voting approaches was conducted. The standout performer is the AdaBoostClassifierET, achieving an accuracy of 87.56%, precision of 88.36%, recall of 86.38%, and an F1 score of 87.36%. Bagging methods also exhibit commendable performance, with the BaggingClassifierET achieving an accuracy of 87.38%, precision of 87.17%, recall of 87.50%, and an F1 score of 87.34%. The research also highlights the significance of base model choices in ensemble techniques, as different base model choices yielded different results in all four techniques. The study surpasses previous work by incorporating a comprehensive set of ensemble techniques, advanced feature engineering informed by time and frequency domain analyses, and a nuanced evaluation of overfitting concerns.
A cam swing roller-follower mechanism is designed for the beat-up motion of a horizontal narrow loom. The system consists of a radial plate-cam driven by a camshaft keyed to the plate cam. A slay bar which act as the beater is attached to the radial swing roller-follower and assembled on the plate cam. A continuous contact between the roller follower and the plate-cam is maintained by a spring attached to the follower and fixed to a reference frame to prevent mechanism bounce. The conceptual design for the mechanism is based on the fundamental generalized synthesis procedure. The topology of the kinematics is developed by using the graph theory method of kinematic synthesis. The forces required to drive the plate-cam and follower system were modeled and the components such as the plate-cam, camshaft, the follower and the drive mechanism were synthesized for smooth operation of the mechanism. Analysis of the force requirement show that maximum impact required to beat the weft into the yarn during weaving is achieved at the maximum plate-cam displacement. The acceleration of the cam plate is controlled in the model at the start and end of motion as boundary conditions to specify some degree of stability for the system.
In this study, the influence of the compression ratio on the performance characteristics of a gasoline engine was investigated in detail using COMSOL simulations. Four compression ratios — 8, 9, 10 and 11 — were investigated at different engine speeds between 1000 and 1800. The analysis focused on power output, braking performance and fuel consumption in order to decipher the complicated relationships between compression ratios and engine dynamics. The results showed a significant increase in power output with increasing compression ratio, highlighting the delicate balance required for optimal power generation. Braking power increased with higher compression ratios, indicating a potential improvement in braking performance. In addition, the study showed a correlation between increased fuel consumption and higher compression ratios, highlighting the need for strategic fuel-saving measures. These results contribute to the understanding of gasoline engine behavior and provide insights into the trade-offs that need to be made when adjusting the compression ratio. Recommendations include experimental validation, exploration of dynamic compression control, research into integrated braking systems, investigation of sustainable fuel strategies and a focus on multi-metric optimization. The observed increase in power output at higher compression ratios highlights an important aspect of engine optimization. Engineers and researchers need to carefully consider compression ratio adjustments to ensure optimal power generation while maintaining efficiency. This insight can guide the development of engines that strike an ideal balance between power and fuel efficiency.
The need for new designs of Groundnut oil expeller is based on the cost and efficiency of the machine especially for the usage in small and medium size industries. It has to be cost effective and light weight to accommodate such demands. The existing Groundnut Oil Expellers in the market are too big and too expensive for these small medium size businesses to invest on. Other limitations are its maintenances aspect as well as its operations. Therefore, series of survey and research have been done to identify the needs and base on that, the Final Design and Specifications were synthesized. The Groundnut Oil Expeller is a screw type machine, which presses groundnut through a barrel-like cavity. Raw material (groundnut) enters one side of the press and by product (cake) exit the other side. The machine uses friction and continuous pressure from the screw drives to move and compress the groundnut. The oil seeps through small openings that do not allow groundnut fibre solids to pass through. Afterward, the pressed groundnuts are formed into a hardened cake, which is removed from the machine. This machine will satisfy the demand for the small and medium size industries because of its design, functionality and price. The measurements of the performance also being analyze by calculating the design efficiency.
The fluid flow pattern that occurs in the bio-diesel production process is related to viscosity, flow velocity, and pressure. Fluid flow is a paramount cause of failure in pipes in several industries. The heat transfer cause across pipes needs to be analyzed to avoid failure during operation. The simulation and visualization of fluid flow in the plant pipes were developed for the pressure drop along with the length of the pipe. Flow patterns was analyzed using a Computational Fluid Dynamics model approach (CFD). The CFD within the ANSYS environment has three important stages, namely pre-processing, finding solutions, and post-processing. Mesh was generated and the material properties were assigned. The boundary conditions were stipulated, and the process analyzed to ensure convergence of the solution in a stable state. High density of the blend was observed for 40% bio-diesel blend and low density at 5% bio-diesel blend. The results of the correlation analysis shows that density is directly proportional to bio-diesel content. The density-composition depict a uniform increasing density value with percentage bio-diesel mixture content. The viscosity slightly increases with bio-diesel content. There is a clear trend of viscosity increasing proportional to bio-diesel content. The simulation ensures that the parameters for the design and fabrication of the bio-diesel reactor as obtained from the simulation results is optimal.
In an attempt to reduce sound radiated from a portable generator, a sound proof enclosure has been developed to absorb effectively the generator noise. This sound proof enclosure is designed and fabricated with locally available materials from the opinion of an idea which aims at easing the pains and stress of receiving the noise radiating from a portable electric generating set. The walls of the enclosure is fabricated by combining panels of foam, composite sawdust and grinded glass and an outer plywood with air trapped in-between the composite and plywood. A reverberation room method is used to measure the noise absorption efficiency of the enclosure using a 950 watts/220 volts rated generator to ascertain the enclosure performance average at 76.40% noise absorption.
This research focuses on the design, analysis, and construction of a biodiesel processing plant with the aim of improving global processes, control, and overall design efficiency. Biodiesel, a renewable energy source, offers environmental benefits and extends engine life. The study addresses the challenges associated with biodiesel usage, such as higher initial costs and potential engine issues, and proposes the use of waste vegetable oil to reduce processing costs. Various reactor designs from past studies are analyzed, emphasizing the need for effective mixing techniques. The research presents a novel prototype reactor and considers the selection of materials, stresses, strains, and insulation for each tank. Additionally, the study explores the use of different heating elements, including mica band heaters and immersion heaters, to achieve the required temperatures for transesterification. The findings also discuss the selection of gear motors and pumps for effective mixing and fluid transfer. The results of the construction and assembly of the biodiesel plant are presented, highlighting the inclusion of various accessories to enhance functionality. Finally, the research emphasizes the economic and environmental advantages of biodiesel production, considering energy consumption and cost savings in the Nigerian context.
