Thermoacoustic refrigerators are emerging devices that make use of meaningful high-pressure sound waves to induce cooling. Despite the accelerated progress in the field of thermoacoustics, knowledge of the heat transfer process in the heat exchange of the devices is still developing. This work applies different soft computing techniques, namely, an artificial neural network trained by particle swarm optimisation (ANN-PSO), adaptive neuro-fuzzy inference system (ANFIS), and artificial neural networks (ANNs) to predict the oscillatory heat transfer coefficient in the heat exchangers of a thermoacoustic device. This study provides the details of the parametric analysis of an artificial neural network model trained by particle swarm optimisation. The solution model considers the number of neurons, the swarm population, and the acceleration factors to develop and analyse the architecture of several models. The regression model (R2) and mean squared error (MSE) were used to evaluate the accuracy of the models. The result showed that the proposed soft computing techniques can potentially be used for the modelling and the analysis of the oscillatory heat transfer coefficient with a higher level of accuracy. The result reported in this study implies that the prediction of the OHTC can be considered for the enhancement of thermoacoustic refrigerators performances.

Activities in the mining industries as a result of rock blasting is the cause of extreme rock vibration which is considered a serious environmental hazard. In most cases, explosives are often used for the disintegration of rocks in opencast mine. One of the major challenges often experienced in mining industries is the case of ineffective use of explosive energy while performing such opencast operation, this could lead to disproportionate ground vibration, often measured by peak particle velocity (PPV). To reduce such ground vibration and environmental impediments, it is important to adopt creative models for the effective prediction of PPV. Considering the inevitable impact on rock mass, neighbouring structures and sometimes on human beings, an accurate prediction of ground vibrations and the evaluation of the aftereffects must be carried out prior to the actual blasting event. This research is an exposition of the prediction performance of a blast-induced PPV using a creative model -Fuzzy Mamdani Model (FMM) and a hybrid algorithm -Adaptive Neuro-Fuzzy Inference System (ANFIS), in mining operation. These models are employed to predict the blast-induced PPV, which is a measurement of the movement or vibration of a single earth particle as the shock waves from a particular location or blasting event moves through the system. Experimental dataset used in this research consists of three (3) input variables (change weight per delay, distance and scaled distance) and forty-four (44) record samples; the peak particle velocity represents the experimental result. The dataset is fed into MATLAB 2020 platform as input parameters. Results obtained using the creative and hybrid algorithms were compared based on root mean squared error (RMSE) and correlation coefficient between the experimental and predicted values of the PPV. The regression values obtained are 0.8487 and 0.97729 for the Fuzzy Mamdani model and ANFIS model respectively. From the result obtained, the best vibration prediction was achieved using the ANFIS model. It can be concluded that the ANFIS model gave a better prediction in terms of speed of computation and prediction accuracy. It is recommended that other hybrid algorithms and metaheuristic techniques be introduced and compared with the existing solution models for effective prediction of PPV in mining operations.