No abstract

In order to provide an effective tool for the simulation of wastewater treatment plant performance and control, a reliable model is essential. In the present study, two different artificial intelligence (AI) models; Adaptive Neuro-Fuzzy inference system (ANFIS), and a classical multi-linear regression analysis (MLR) were applied for predicting the performance of Abuja wastewater treatment plant (AWWTP), in terms of Conductivity, pH, Iron content, BOD, COD, TSS and TDS. The daily data were obtained from Abuja Wastewater treatment plant, for this purpose, single and ensemble models were employed to compare and improve the prediction performance of the plant. The obtained result of single models proved that, MLR model provides an effective analysis in comparison to the other single model. The result showed that, conductivity influences the performance and efficiency of the water treatment plant by an increased efficiency performance of AI modelling up to 99.6% testing phase and 6.8% Error value of same phase. This shows that MLR model was more robust and reliable method for predicting the Abuja WWTP performance.

Problem statement: Multiple-Input Multiple-Output systems (MIMO) were regarded as one of the most promising technologies in field of wireless communication. Generally considered as one of the several forms of smart antenna technology, it offers considerable increase in data throughput and link range without additional bandwidth or transmit power. The general idea involves the use of several antennas at the transmitter and the receiver to improve system performance. One of the approaches employed in combating ISI in MIMO transmission was through the use of equalizers. Approach: In this study a proposed MIMO system was simulated using MATLAB software. The different equalization schemes Zero Forcing (ZF) equalizer and Minimum Mean Square Error (MMSE) which aid in the elimination of Inter Symbol Interference (ISI) thus improving overall performance were compared to analyze the BER of the designed system. Results: From the simulation results, the MMSE equalizer clearly had a better performance over the ZF equalizer in the region of about 3 dB. Conclusion: MIMO transmission with MMSE equalization offers greater performance over ZF equalization. This helps in nullifying the effects of ISI thus improving overall performance. Thorough understanding of these techniques provides a good platform for future research in areas such as MIMO-OFDM.

No abstract

With the advent of several fault detection techniques in modern control systems design, this paper adopted the Artificial Neural Network (ANN) Fault Detection scheme for the Fault Detection of the Attitude Control System for a Communication Satellite. In satellite applications, telemetry data can be very large, and ANN is best suited for network modeling involving large sets of data. The availability of real satellite data from Nigcomsat-1R communication satellite provided a practical platform to assess the fault detection algorithm. Results obtained showed a good correlation between raw satellite telemetry data and Neural Network model-generated results for subsequent fault detection. The fault detection models were able to detect faults, log them and provide a notification to enhance subsequent isolation and rectification. Momentum Wheel Speed and Torque were used to investigate the performance of the wheels while the Momentum Wheel Voltage and Current helped to monitor the wheel’s health state. A fault is detected if the absolute difference between original output (MW Torque) and the NN Torque output is greater than 0.012. With this, an accuracy of 100% and mean squared error of 9.8489e-6 were achieved.