Browsing by Author "Davis, Francis"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Machine learning of redundant energy of a solar PV Mini-grid system for cooking applications
    (Solar Energy, 2023) Opoku, Richard; Adjei, Eunice A.Mensah, Gidphil; Adjei, Eunice A.; Dramani, John Bosco; Kornyo, Oliver; Nijjhar, Rajvant; Addai, Michael; Marfo, Daniel; Davis, Francis; Obeng, George Yaw; 0000-0001-8766-3402; 0000-0003-2702-6465; 0000-0002-7945-8676; 0000-0002-3640-2664; 0000-0001-8886-7853
    Solar PV mini-grids are increasingly being deployed in off-grid and island communities especially in sub-Saharan Africa (SSA) countries to meet household energy demand. However, one challenge of solar PV mini-grids for community energy supply is the mismatch between the PV energy generation and household energy demand. PV mini-grid energy generation is highest in the afternoon whilst household energy demand is highest in the mornings and evenings, but lowest in the afternoons. This mismatch creates redundant energy generation during peak sunshine hours when battery energy storage is full, leading to low profitability for mini-grid systems. In this study, four machine learning models have been applied on an installed 30.6 kW mini-grid system in Ghana to ascertain the level of the redundant energy. The study has revealed that redundant energy exists on the mini-grid, in the range of 56.98 – 119.86 kWh/day. Further analysis has shown that the redundant energy can support household cooking energy demand through sustainable thermal batteries. With the four machine learning (ML) models applied in predicting the redundant energy, the most accurate ML model, K-nearest Neighbour Regressor, had a root mean square error (RMSE) of 0.148 and a coefficient of determination (R2 ) value of 0.998.
  • Thumbnail Image
    Item
    Monitoring of turning variables using acoustic emission technique
    (2003) Davis, Francis
    This thesis work discusses the monitoring of turning variables such as cutting speed, feed and tool condition based on factorial experimental design method of acoustic emission signal responses. In cutting operations, acoustic emission provides useful information concerning the tool wear condition because of the fundamental differences between its source mechanisms in the rubbing friction on the wear land of the single point tool. In this study, effects of cutting speed, feed and tool condition on the acoustic emission signal are investigated using acoustic emission’s energy, amplitude, and frequency response and 2 factorial design for turning operation. Cutting tests were performed using high-speed steel under dry conditions. Calculated effects, standard errors at 95% confidence level, and models governing the acoustic emission response to the cutting conditions have been generated from the acoustic emission signal responses. The generated models revealed that acoustic energy response is affected by significant interactions between cutting speed and feed, and insignificant interactions between cutting speed and tool condition, while the acoustic amplitude response is affected by insignificant interactions among cutting speed, feed, and tool condition. These results suggest that tool wear can be detected by monitoring the variations of acoustic energy, and amplitude responses during machining processes.