ABUAD Journal of Engineering Research and Development (AJERD)

Artificial Neural Network for the Clustering of Vibration Signals for Condition Monitoring of Rotating Machines

Eyere Emagbetere — 2025-01-18

Vibration analysis is commonly used to provide valuable insights into the condition of a machine, which is crucial for ensuring reliability and reducing maintenance costs. However, analysis of vibration signals using artificial neural network (ANN) is mostly via development of classification models, which cannot be suitably applied to several varied machine types and specifications. This study investigates the use of ANN in the clustering of vibration signals for machine condition monitoring of several rotating machines. Data obtained from different rotating machines for 4 years was utilized for the study. The data contained values of vibration signals taken at 12 different pickup points, power ratings, year and equipment location. The obtained data was preprocessed and analyzed statistically. Then, silhouette scores and within-cluster sum of squares (WCSS) were used to obtain the optimum number of clusters for the analysis. Afterwards, different clusters were created using ANN, which were then explored to gain insights for potential applicability of the technique for assessment of the conditions of rotating machines. The result of ANOVA showed that there were significant variations between readings obtained from different pickup points and readings obtained from the different machines, with p-values far less than 0.05 for both cases. It was found via silhouette and WCSS that 9 was an optimum number of clusters for the analysis. Calculated mean of standardized values informs that 6 clusters contained machines with different forms of faults, having positive mean values far greater than 0. Also, there were 2 clusters with machines having good working conditions with negative mean values, while one cluster had machines that were moderately okay with mean values close to 0. The study has shown that ANN can effectively cluster a set of machines based on their conditions using vibration signals taken at different pick-up points. The developed framework is a suitable alternative to ANN-based classification methods which have limited applicability.

Implementation of a Smart Home Intruder Detection System using a Vibrometer and ESP 32 CAM

Samuel Owoeye — 2025-01-18

Nigeria today is rife with occurrences of intruders breaking into homes at every slight opportunity. The topic of security is quite important; hence this paper presents the development and implementation of a Smart Intruder Detection System utilizing the ESP32-CAM board, the Vibrometer and the ATMega328P microcontroller to enhance lighting, security, and surveillance functionalities. The ESP32-CAM serves as the central control unit, leveraging its built-in Wi-Fi and camera capabilities, while communicating with the ATMega328P microcontroller responsible for managing lighting, security, and surveillance components. The Vibrometer adds a vital layer of security by detecting vibrations associated with forced entry attempts. Upon sensing significant vibrations, the Vibrometer triggers the ESP32-CAM to start an immediate recording of potential intrusions. In the realm of lighting control, the ATMega328P regulates diverse light sources such as LEDs and smart bulbs. The ESP32-CAM facilitates a user-friendly experience, enabling seamless control and automation of the lighting system through a dedicated mobile application or voice commands. For surveillance purposes, the ESP32-CAM captures real-time video, streaming it to the user's mobile device or a centralized monitoring station. The ATMega328P contributes to the system's intelligence by supporting motion detection algorithms, which, in turn, trigger automated alerts and activate lighting or alarm systems in response to detected movement. The precision performance of the components was carried out and the average precision for all the components was 95%. The synergistic integration of the ESP32-CAM board and ATMega328P microcontroller results in a cohesive and intelligent smart home automation solution.

Effect of Palm Kernel Shell Ash Supplement with Egg Shell Ash on Stabilized Lateritic Soil for a Road Work

Sulaiman Olayinka Subair — 2025-01-18

Lateritic soil serves as a fundamental material in road construction; however, its engineering properties can be significantly improved through the use of additives. In Nigeria, the abundant generation of agricultural by-products—such as palm kernel shells, eggshells, and wood residues—presents challenges related to waste disposal and management. These materials can contribute to environmental degradation, including air and water pollution, and adversely affect local ecosystems. This study explores the effects of Palm Kernel Shell Ash (PKSA) and Egg Shell Ash (ESA) on the stabilization of lateritic soil for use in road pavement applications. Comprehensive geotechnical testing was conducted on natural lateritic soil to assess various parameters: Specific Gravity (SG), percentage passing sieve No. 200 (F-200), Liquid Limit (LL), Plastic Limit (PL), Plasticity Index (PI), Maximum Dry Density (MDD), Optimum Moisture Content (OMC), and both unsoaked and soaked California Bearing Ratio (CBR). These parameters were also measured for stabilized soil samples incorporating 4% PKSA and varying percentages of ESA (0%, 2%, 4%, 6%, 8%, and 10%) by dry weight of the lateritic soil, in accordance with West African Standards (WAS). The analysis revealed that the natural lateritic soil exhibited an SG of 2.53, F-200 of 27.00%, LL of 29.00%, PL of 17.20%, PI of 11.8%, MDD of 1820 kg/m³, OMC of 11.5%, and CBR of 22%. Conversely, the stabilized samples demonstrated SG values ranging from 2.3 to 2.5, F-200 between 27% and 28%, LL from 27.0% to 30.0%, PL between 10.0% and 17.2%, PI ranging from 10.3% to 11.8%, MDD between 1860 and 2000 kg/m³, OMC values between 8% and 11%, and CBR results from 25% to 80%. Notably, the combination of 4% PKSA and 8% ESA resulted in significant improvements in the engineering properties of the soil, rendering it suitable for use as sub-base material in road construction. Therefore, this blend is recommended for effectively stabilizing lateritic soil for road infrastructure projects.

Water Quality Assessment of Selected Wells in the Farmer-led Irrigation System in Anloga District, Volta Region, Ghana

Henry Evonameh Igbadun — 2025-01-18

Increased groundwater extraction for irrigation is leading to the intrusion of saline seawater into many wells in some communities in Anloga District, Volta Region, Ghana, with resultant adverse effects on crop productivity. This study investigated the water quality of selected wells in four communities of the district for their suitability for irrigation. Water samples were collected from 10 representative wells, purposively selected out of 60, to determine the pH, electrical conductivity, total dissolved salt by means of a pH/EC/TDS/Temperature portable meter, and the concentrations of sodium, potassium, calcium, magnesium, sulphates, chlorides, bicarbonate and nitrate, using standard chemical laboratory procedures. The geochemical characterization of the sampled water sources was carried out using the Piper trilinear diagram, and revealed the dominance of Na-Cl facies of the groundwater in Tegbi, Whuti and Anyanui, suggesting seawater encroachment connected with groundwater abstraction. The water samples from wells in Woe indicated the Ca-Mg-Cl-SO₄ mixed type and are considered suitable for irrigation. About 50% of the sampled wells could be classified under the high salinity-low sodium hazard (C3-S1), 20% are under very high salinity-medium sodium hazard (C4-S2), another 20% under very high salinity-high sodium hazard (C4-S3) and 10% under medium salinity-low sodium (C2-S1) classes. These wells are prone to salinity, and farmers’ discretion is recommended through the adoption of conditional use of the irrigation water such as growing of salt-tolerant crops.

Technical Losses across Distribution Networks in Nigeria and Mitigative Measures: A Review

Gerard Nonso Obiora — 2025-01-18

The different distribution companies (DisCOs) in Nigeria constantly battle with the issue of technical losses on their respective distribution networks. And this is one factor that heavily affects their revenue. Though, technical losses are inevitable because they cannot be totally eliminated but can be rather reduced. This paper identifies lengthy distribution lines, worn-out equipment, insufficient size of conductors of distribution lines, no growth provision of system, unequal load distribution of the three phases of low tension lines, low voltage, overloading of distribution lines, load factor effect, low power factor, abnormal operating conditions, transformer sizing and selection, location of distribution transformers, feeder length, poor workmanship, use of overrated distribution transformers, efficiency of equipment and lack of proper maintenance as some of the root causes of technical losses. In addition, practicable solutions are provided on ways the identified technical losses can be curbed on the networks of the distribution companies if implemented. The focus of this survey is to present the prevalent factors that induce technical losses on the DisCOs networks and the measures that can be taken to limit the occurrence of this class of losses. This assessment will aid industry experts, potential investors and other investigators in taking appropriate decisions on projects within this field.