Sustainable cooktop design: A neural factorial design approach

The predicted effects of global warming for the environment and for human life are numerous and varied. The main effect is an increasing global average temperature. From this flow a variety of resulting effects, namely, rising sea levels, altered patterns of agriculture, increased extreme weather events, and the expansion of the range of tropical diseases. In some cases, the effects may already be occurring, although it is generally difficult to attribute specific natural phenomena to long-term global warming. To combat the global warming problem, the regulatory bodies(such as the Electrical & Mechanical Services Department of the HK SAR Government), gas suppliers and manufacturers of cooking appliances in Hong Kong are trying their best to find ways of improving energy efficiency and reducing greenhouse gas emissions. In view of the number of controllable factors and responses to be studied, Factorial Design is often used for the empirical investigations. Design of Experiments(DOE) is a powerful tool that can provide information not otherwise obtainable from single-factor experiments. There are, however, limitations in its use: these are due more to practical than to theoretical constraints. One such limitation is a logistical one, applying to the availability of resources (e.g., time, labor, and the pool of experimental units). In this regard, the authors proposed to combine the DOE technique with the neural network approach for a quick solution of multiple input and multiple output(MIMO) problems. Potential time and cost savings of the Neural Factorial Modeling approach is illustrated through the sustainable design of a pre-mixed cooktop burner.