Theses/Dissertations/Projects
Permanent URI for this collection
Browse
Recent Submissions
Item Metadata only A Comparative Analysis of Mathematical and Machine Learning Based Models for Predictive Maintenance in a Production Line(Bells University of technology, Ota, 2022-08-10) AINA, Yusuf Amuda; Dr. B. A. BelloMaintenance is an activity to ensure that production line equipment are in satisfactory condition and reliable. Thus, the optimum goal of maintenance is to ensure that the performance of the equipment is satisfactory by minimizing downtime and reducing cost related to downtime. The complexity of production line has changed the tradition decision- making process regarding maintenance management through the use of artificial intelligent based predictive maintenance in order to make more efficient real-life decision. This study developed a mathematical and machine learning predictive maintenance models using production line parameters to predict machine failure. Fit retrogression model was used as the mathematical model and Adaptive Neuro Fuzzy inference system (ANFIS based) was used as the adopted machine learning model. Data obtained from the production line revealed that the fault is subject to production line parameters such as main pressure, operating voltage, current consumption, vibration and temperature. Performing statistical analysis revealed the adequacy of the models with coefficient of determination (R2) of 83.99% for number of fault. Training of datasets with ANFIS revealed a convergence at epoch number of 3, and with minimum root mean square error (RMSE) of approximately zero (0.000161), indicating the significant training approach of the ANFIS training of the dataset. Evaluation of the two models (mathematical and machine learning) showed they give better prediction of the number of faults, as their predicting values were closerU to that obtained from the equipment . Comparatively, machine learning (ANFIS based model) showed better predicting strength compared to the mathematical model. This is because ANFIS adopts the learning and performing system of artificial neural network (ANN) and fuzzy logic.Item Metadata only A Comparative Analysis of Mathematical and Machine Learning Based Models for Predictive Maintenance in a Production Line.(Bells University of Technology, Ota., 2022) AINA, Yusuf Amuda; Dr. Mrs. Olamide O. OlusanyaMaintenance is an activity to ensure that production line equipment are in satisfactory condition and reliable. Thus, the optimum goal of maintenance is to ensure that the performance of the equipment is satisfactory by minimizing downtime and reducing cost related to downtime. The complexity of production line has changed the tradition decision- making process regarding maintenance management through the4 use of artificial intelligent based predictive maintenance in order to make more efficient real-life decision. This study developed a mathematical and machine learning predictive maintenance models using production line parameters to predict machine failure. Fit retrogression model was used as the mathematical model and adaptive neuro fuzzy inference system (ANFIS based) was used as the adopted machine learning model. Data obtained from the production line revealed that the fault is subject to production line parameters such as main pressure, operating voltage, current consumption, vibration and temperature. Performing statistical analysis revealed the adequacy of the models with coefficient of determination (R2) of 83.99% for number of faults. Training of datasets with ANFIS revealed a convergence at epoch number of 3, and with minimum root mean square error (RMSE) of approximately zero (0.000161), indicating the significant training approach of the ANFIS training of the dataset. Evaluation of the two models (mathematical and machine learning) showed they give better prediction of the number of faults, as their predicting values were closer to that obtained from the equipment. Comparatively, machine learning (ANFIS based model) showed better predicting strength compared to the mathematical model. This is because ANFIS adopts the learning and performing system of artificial neural network (ANN) and fuzzy logic.Item Metadata only Voltage Profile Enhancement on the Nigerian 330-KV Grid Using Series -Shunt Reactive Power Compensation Technique.(Bells University of Technology, Ota., 2020-06-10) SALAMI, Hamed Temitope; Prof. R. L. SalawuThe Nigeria 330 kv power systems is characterized with major constraint such as low voltage profile and power loses resulting to negative effects on power generation and transmission systems. The aim of this study is to enhance the Nigeria 330-kv grid voltage profile using combined series and shunt compensation for enhancing the operation of the system. The load flow study using Newton -Raphson -based method was carried out to analyze the steady state operation of the system for the base case ,as this method convergence faster and its simplicity attribute as compared to their solution methods . The series compensation was incorporated, followed by the shunt compensation and then combined series and shunt compensation were incorporated inro system in sequential order. Capacitor Banks sizing was analyzed and adequate placed at the affected buses to inject more reactive power necessary to increase the voltage profile of the affected lines. MATLAB/SIMULINK software was used to carry out the simulation analysisItem Metadata only Development of Dual-Band E-Patch Microstrip Antenna Using Perturbation and Full-Wave Matching for Wireless Local Area Network Application(Bells University of Technology, 2021-08-12) ALFRED-ABAM, Fubara Edmund; Prof. R.I SalawuTransmission and reception of signals are associated with antennas which are transducers for either radiating or receiving Electromagnetic (EM) waves. However, a single Microstrip Patch Antenna (MS) exhibits inherent narrow impedance bandwidth which restricts faster communication throughput. This study aimed at developing a dual-band E-patch microstrip antenna using perturbation and full-wave matching for Wireless Local Area Network (WLAN) application. It examined how the antenna design targets the center operating frequencies of 2.4 GHz and 5.8 GHz for possible range and speed. The transmission line and the full-wave models were employed to analyze the patch antenna and attain the associated input impedance Driving Point Function (DPF) for matching characteristics. This approach was used to quantify the reduction in reflections for improved Radio Frequency (RF) network output. Also, the antenna impedance bandwidth was then compared for the simulated and the fabricated models based on the reflection coefficient. The dimension of the antenna width and length was 31 mm by 25 mm, in which rectangular slots were etched on the patch surface with the possibility of varying the designed slots and feed to attain optimal performance. A 1.5 mm thick Fiber Reinforced Epoxy Flame Retardant 4 (FR4) substrate, with a loss tangent of 0.02 was terminated with a subminiature version A (SMA) connector and a 50 S coaxial cable. A parametric analysis was carried out by using an Advanced Design System (ADS) full-wave simulation tool, on the other hand, the fabricated antenna was tested using a Vector Network Analyzer (VNA) based on Voltage Standing Wave Ratio (VSWR), bandwidth, and return loss (Si) performance indices. The results showed that the antenna Si, at the resonating frequencies were - 40 dB and - 35 dB for the simulated lower and higher bands, respectively while the corresponding values obtained for the fabricated model were - 36 dB and - 31 dB. This represents the desired value of the reflected signal based on IBEE Std. 149, having an associated VSWR of less than 2. The obtained EM radiation and antenna efficiencies were 97% and 94%, respectively which justify a properly matched antenna. The results further revealed an impedance bandwidth of 31% and a nearly omnidirectional radiation pattern with a peak directivity and gain of 7.4 dBi and 3 Bi demonstrating a satisfactory radiation property. The lower resonant frequency of the design was 2.4 GHz with a bandwidth of 120 MHz, ranging from 2.35 GHz to 2.47 GHz, while the higher resonant frequency was 5.8 GHz with a bandwidth of 260 MHz ranging from 5.63 GHz to 5.89 GHz signifying a wideband feature. The significance of the E-patch antenna design is that it can contribute to a simultaneous dual-broadband radiation mode useful for high-performance wireless communication with less noise interference, having a forward compatibility with recent Wireless Local Area Network (WLAN) technology.Item Metadata only Digitization of Energy Production and Consumption in Beverage Industry(Bells University of Technology, 2022-05-12) ALAWODE, Jeremiah Olakunle; Dr.Mrs. Olamide O.OlusanyaEnergy is a major driving force of industrial operations. Virtually nothing can be done without consumption of one or more types of energy or conversion from one form to another by the general law of conversation of energy. Quantifying these energies and accurately costing same has been a major concern as only a rough estimated values are usually assumed. In this research work, digitization of steam energy production and consumption in beverage industry were focused on. In the methodology adopted, flow meters identification and compatibility for energy digitization was ascertained. Initial setup of the flow meter was carried outland each flow meter wired using the digital input terminals selected for the plus input signals. This is responsible for the totalizer value (initially being collected manually and locally from each flow meters). Secondly, the identified pulse input for each flow meter was programmed in the PLC using the ladder logic programming language. This involves creating a unique tag name to identify the flow meter, as well as programming the continuous routine responsible for totalizing the flow per pulse during each flow measurement cycle. Afterwards, the connectivity configurations of each flow meter tags in the server were carried out, the OPC\OLE path is configured to ensure that data from the flow meter through the PLC gets to the digitization server. Finally, the manually obtained data from flow meter is compared with the digitized data from the server. The digital manufacturing operation(DMO)server results and the ones manually collected are compared and analyzed using the SPSS software tool for data analysis . In conclusion, the results show that Digitization of energy production and consumption in Beverage industry' is a practicable solution to solve energy measurement problems in any establishment. This solution can also be extended to other energy utilities such as water, PMS, diesel, gas, and electricityItem Metadata only Reliability Assessment of 11KV Power Distribution Sytem(Bells University of Technology, 2022-05-12) OKPO, Mba Mazwell; Dr. Olamide O. OlusanyaThe electricity value chain of our country is plague with a lot of problems which has a negative impact on the reliability of the power system. Faults has been idenitified as one of the major problems affecting the reliability of the power supply. Each time there is a power interruption, there is always an energy loss which disrupt processes of the end-users resulting to economic waste especially for industrial users. This study aims at assessing the reliability of 11KV of a KV power distribution system, the two approaches used were fault classification and category. analysis using tripping frequency and reliability analysis using CAIFI, CAIDI, SAIFI, SAIDI. March and August for year 2020 and 2021. The data for 2020 were collected and analyzed. The results of the analysis was used to develop reliability techniques which was implemented on the system in the year 2021Item Metadata only Modelling and Simulation Of A Remote Based Maintenance System, For A Reactor In A Chemical Laboratory Of A Beverage Industry(Bells University of Technology, 2022-05-12) IMONIGIE, Yussuf Ameen; Dr. Olamide O. OlusanyaThis dissertation has clearly studied Modelling and Simulation of A Remote Based Maintenance System for a reactor in a chemical laboratory of a manufacturing industry a case study Nestle plc using internet of things (IOT). Here, the considered equipment is the Reactor. i.e Continuous Stirred Tank Reactor (CSTR), as shown in figure 9 and 10, is a computer controlled, and designed to demonstrate the behaviour of a reactor used for homogeneous reactions liquid (production of ethanol) used in production or institutions.It was considered due to inevitable deterioration and need for maintenance of system. WIth temperature as the process variableItem Metadata only Reliability Assessment of Power Distribution Sytem Case Study of Agbowo 11kV Substation(Bells University of Technology, 2022-05-12) OKAGA, Ezekiel Oluseyi; Dr D.O. AkinyeleDistribution network form a non-negotiable link in the hierarchical structure of conventional power sytem, it is the arm of power systems through which customers' demand for energy is met. However, the ability of the power system to meet or balance the customers' load demand results in outages and load shedding, which raises a question of system reliability. It is therefore paramount to identify the system components that are susceptible to failure in the power system to ascertain those components that can occasion loss of supply to customer . The ism of this study is to evaluate the reliablity of a secondary distribution system using Agbowo 11 KV feeder as a case studyItem Metadata only Design and Performance Analysis of Solar/Biodiesel Based Microgrid System for Isolated Communities(Bells University of Technology, Ota, 2023-05-16) ADESHINA Olatunbosun Adeonipekun; Dr D.O. AkinyeleThe problem of erratic supply from and the lack of access to the national grid has attracted a growing interests in renewable energy-based systems for addressing the energy shortage issue.This study then focuses on the design and performance analysis of solar/bio diesel micro grid for isolated communities. It uses the Hybrid Optimization Model for Electric Renewables (HOMER) Pro Microgrid software to determine the PV array, battery, inverter and the biodiesel generator sizes required to support the isolated house demand of 89.55 kWh/day.