The existence of the new improvement system for Human Machine System (HMS) is called as Human Adaptive Mechatronic (HAM) system. The main difference between these two systems is the relationship between human and machine in the system. HMS is one way relationship between human and machine while HAM is a two way relationship between human and machine. In HAM, not only human need to adapt the characteristics of machine but the machine also has to learn on human characteristics. As a part of mechatronics system, HAM has an ability to adapt with human skill to improve the performance of machine. Driving a car is one of the examples of application where HAM can be applied. One of the important elements in HAM is the quantification of human skill. Therefore, this project proposed a method to quantify the driving skill by using Artificial Neural Network (ANN) system. Feedforward neural network is used to create a multilayer neural network and five models of network were designed and tested using MATLAB Simulink software. Then, the best model from five models is chosen and compared with other method of quantification skill for verification. Based on results, the critical stage in designing the network of the system is to set the number of neurons in the hidden layer that affects an accuracy of the outputs.

This project is to study the effect of welding preheat on metallurgical analysis and microstructural development. Variables such as current, speed of welding and size of specimen were fixed. In the present work, a mild steel plate with thickness of 100 mm and width size of 20 mm was used. SMAW (Shielded Metal Arc Welding) technique was chosen as it is the easiest way to perform and widely used in oil & gas and marine industries. Three different preheat temperatures were performed during the study; ambient temperature (no preheat), between 60 °C to 70°C and greater than 200 °C. The study emphasizes on the minimum preheat temperature that produce good quality welding by taking into account some of metallurgical aspects; microstructure and macrostructure development, hardness distribution at important areas in weld (Heat Affected Zone, parent metal and weld area) through thickness. From this study, code American Welding Society (AWS) D1.1 was used as a reference and it stated that for plate that has 100 mm thickness the preheat temperature should be in the range of 60 °C and 70°C. The result of microstructure and macrostructure showed that the depth of penetration was not vary too much. Hardness measurement, macro and microstructure observation were performed in order to obtain a good correlation exist between these parameters studied.

Properties enhancement through surface modification has been established as a method to improve the dispersion quality of case hardening treatment. Improvement of dispersion thickness layers resulted in properties enhancement of metallic material. This study investigates the effect of shot blasting parameters which are single (SB) and double (DB) sand blasting on boronizing dispersion layer of 304 stainless steel. Boronizing treatment is conducted using paste boron at temperature of 900˚C for 6 hours holding time. The dispersion layer measurement and phase identification were evaluated through optical microscope and XRD analysis. Vickers hardness test and surface roughness analysis were also conducted .The result shows that noticeable enhancement of dispersion layer thickness was observed after conducting double sand blasting as compared to single sand blasting. Thicker dispersion layer leads to the increment of hardness value and also enhancement in surface roughness properties.

No abstract

No abstract