Dr Edward Ofoegbu

The integration of advanced technologies into aerospace systems, par- particularly within hydraulic systems such as landing gear mechanisms, has introduced new dimensions of complexity and vulnerability. This paper discusses the methods of fault detection from a historical perspective to the current state of the art adopted in industry for real-time detection of faults in hydraulic systems deployed in aerospace. A review of fault detection methods ranging from the manual method, the threshold method, the statistical method, the model-based method, the signal-based method, the knowledge-based method and time frequency analysis method, and the artificial intelligence method, Explainable AI (XAI) was explored and discussed in this paper. The review reiterated that while detection methods, such as manual inspection and threshold-based monitoring, are straightforward to implement, they fail to deliver precise results when detecting complex faults. Model-based and AI-driven advanced techniques enhance precision at the expense of demanding greater computational power and sufficient data availability.

Energy conservation and its efficient utilization especially in cloud data centers has been a subject of discourse amongst numerous stakeholders. Advancement in information technology tools provides a solution to automating the process of electricity metering as well as remote load control alternatives. This paper presents an energy meter reader implemented with a microcontroller based logic methodology fused with a building automation system to implement remote load control by home owners using SMS from a GSM phone. A password based relay circuit was incorporated to ensure secure switching by the user. The system when deployed can enable users query and set energy consumption rates remotely so as to reduce the cost on final consumers as well as conserve energy. This is could be a useful system in the green-based design of cloud data centers.

The transformation of the power grid from traditional methods into smart grids for the generation, transmission, distribution, and utilization of electric energy reduces the dependency on fossil fuels, thus taking a step towards environmental sustainability. This research paper simulates a smart grid's behavior when integrated with a renewable energy source. The grid network topology of a power system was modeled and simulated in MATLAB/SIMULINK, where the model consisted of renewable energy resources (RER's) having a series of solar panels, redundant power generating stations, a transmission infrastructure, and a power utilization section for 3-phase high voltage industrial load and low voltage domestic load, respectively. The results of the study showed that there is power loss and signal distortion in the output voltage when multiple generators are integrated. These harmonics can be easily filtered out when the integration is done between the generator and a renewable energy resource (RER) using properly designed Resistor-Inductor-capacitor filters and booster circuits. The results further demonstrated that when integration was accomplished between the generator and the RERs, a stable output voltage of 0.6e4 V was obtained, given a generator capacity of 6600 V. The industrial and domestic load also showed minimal instability by maintaining an output of 1100/440 V, respectively, before and after integration. The study also showed that RERs can be used to support the power supply to the grid to maintain its supply voltage and the overall stability of the system. However, RERs cannot withstand supplying a power grid on their own.

Battery management systems (BMS) are critical in ensuring the performance, reliability, and safety of battery systems through accurate estimation of the State of Charge (SOC) of batteries. As on-board SOC estimation, together with other functionalities by the BMS can result in its high design complexity, high cost, and high energy consumption, this study explores a data-driven estimation of a Lithium battery state of charge (SOC) while discharging, using simple linear regression, ensemble methods, and neural networks respectively to ensure an accurate low time complexity solution as compared to existing methods. A known dataset of 835,248 records from Li [NiMnCo]O2 (H-NMC)/Graphite + SiO battery was used to train and test each model to determine the best fit. This study determined that neural networks are the models of choice for SOC prediction instead of linear and ensemble regression. Still, also the wide tri-layered feed-forward neural network proposed in this study showed great results by having a maximum error percentage of less than 1 %, and a mean squared error (MSE) of 1e-08, which is similar to or better than what is obtainable in other more complex deep neural network variants such as the Gated recurrent unit recurrent neural network (GRU-RNN), with an MSE of 1e-06 and similar load classifying neural network models with an error percentage of 3.8 %. The FFNN proposed in this study also has the advantage of having lower technical and time complexity computational costs required for active fault estimation in thin client devices such as a BMS.

In recent years, the application of Indoor Positioning Systems (IPS) has experienced a significant increase in demand, with the aging of the world’s population and their changing lifestyles. While outdoor positioning systems, such as the Global Positioning System (GPS), have significantly advanced over the years, indoor positioning has been restrained by the limitations of the employed technologies. This paper presents a hybrid wireless positioning system able to locate wearables indoor accurately. It is based on the Wi-Fi and Bluetooth technologies, by using trilateration to determine the position of Bluetooth low energy (BLE) wearable devices with an accuracy of up to 1.8 meters. A graphical user interface (GUI) was used to illustrate the performance of the proposed systems, by allowing users to visualize the captured data in two dimensions and three- dimensions in real-time.

Gas turbines are a key player in the energy generation sector and thus form a key component in energy systems as a critical infrastructure. The determination of key parameters in optimization and efficiency of the gas turbines are of utmost importance to increase their power conversion efficiency. This paper presents a simple power estimation model for a gas turbine considering all its parameters. 7412 multivariate data records from the UCI Machine Learning Repository were used in the development of a linear prediction model for estimating the turbine energy yield for a combined cycle power plant. Simulation results show that the inlet temperature of the turbine is the most critical parameter that predicts its energy yield capacity, while ambient atmospheric conditions of temperature, humidity and pressure do not predict its energy yield capacity.

Applications in harsh environments greatly suffer from intermittency faults in their interconnections/wirings. Due to the erratic behavior of intermittency that causes signal irregularities, it is tough to distinguish irregularities from an actual transmitted signal, particularly in the earlier stages where signal abnormalities mainly resemble noise. This paper explores step changes in the resistance of a wire caused by broken strands as a failure parameter. Thus, a test rig was designed to emulate the ageing mechanism of the wire. with results of the study highlighting that resistance step changes could effectively be used to locate intermittency faults in low-power cable applications.

Autonomous vehicles otherwise regarded as self-driving vehicles are poised to be the next generation of technological advancement in the transportation sector globally. They offer superior value for money with regard to the cost of operation, excellent safety records, and many other benefits. Cities around the globe have adopted it even as research and development efforts are ongoing. This study investigates the role autonomous vehicles could play in Africa, especially as it relates to transportation inclusivity. The study determined that there are lots of inclusivity issues beguiling African nations ranging from religious, financial, educational, and cultural issues and was able to highlight how the adoption of autonomous vehicles can aid to solve issues relating to stigmatization and social exclusion.

Stock trading, used to predict the direction of future stock prices, is a dynamic business primarily based on human intuition. This involves analyzing some non-linear fundamental and technical stock variables which are recorded periodically. This study presents the development of an ANN-based prediction model for forecasting closing price in the stock markets. The major steps taken are identification of technical variables used for prediction of stock prices, collection and pre-processing of stock data, and formulation of the ANN-based predictive model. Stock data of periods between 2010 and 2014 were collected from the Nigerian Stock Exchange (NSE) and stored in a database. The data collected were classified into training and test data, where the training data was used to learn non-linear patterns that exist in the dataset; and test data was used to validate the prediction accuracy of the model. Evaluation results obtained from WEKA shows that discrepancies between actual and predicted values are insignificant.