Abstract
Artificial intelligence (AI) techniques have a natural harmony that can be made use of to develop prominent computing practices that make tasks easier to perform. Today, soft computing techniques have been applied in various engineering fields, and industrial developments. This integration has proven to be beneficial, with the many technological and performance enhancement in many systems. Sensible use of soft computing techniques leads to the development of systems with enhanced performance. This work proposes the use of an Artificial Neuron Network (ANN), a hybrid Artificial Neural Network trained by Particle Swarm Optimization (ANN-PSO), a Fuzzy Mamdani Model (FMM), and an Adaptive Neuro-Fuzzy Inference System (ANFIS) to model and analyse typical mechanical and industrial systems. The models are built using readily available datasets to illustrate the approaches proposed in this study. Four different case studies have been investigated in this study, namely: 1. Supplier selection in a manufacturing system, 2. Blast-induced vibration in underground mining operations, 3. Stirling engine performance and 4. Oscillatory Heat Transfer of Thermoacoustic systems: Supplier selection in a manufacturing system is highly complex, due to the stochastic nature and structure of organizations, thereby necessitating a shift from the rule of thumb and classical methods of supplier selection to a reliable technique. This study proposes the use of a hybrid computational intelligence technique, Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for effective prediction and Sustainable Selection of Suppliers (SSS). This hybrid modelling configuration was applied in a paint manufacturing company to select the best possible supplier. Information obtained from the company within the period of investigation was fed into the model. The result obtained shows a faster and more reliable prediction of the creative model...
Ph.D. (Mechanical Engineering)