Ali Musyafa

Duelist algorithm for optimisation of safety instrumented system at distillation column based on RAMS + C

Abstract This paper describes the optimisation of safety instrumented system at distillation column based on reliability, availability, maintenance, safety, plus cost using duelist algorithm. Safety instrumented system maintain operating condition in the safe regime when normal operation over the allowable limits. Diversity redundancy was implemented as allocation redundancy. The requirement of safety instrumented system has been appointed by international standard, International Electrotechnical Commission 61508. The objective of this study is to achieve the lowest value of lifecycle cost that affected by average probability of failure on demand and spurious trip rate value. Average probability of failure on demand is involved by failure rate danger that has an effect on safety instrumented level value; meanwhile, spurious trip rate is influenced by failure rate safe that has an effect to the product losses caused unscheduled shutdown. The field instruments subsystems are provided by utilising one of or all different technologies. The best optimisation solution utilises vote 1 out of 1 for all subsystem with smart transmitter technology and air-operated actuator. Its solution obtained lifecycle cost 1,139,898 USD, average probability of failure on demand 7181 × 10−02/h and spurious trip rate 4844 × 10−05/h.

Extreme learning machine approach to estimate hourly solar radiation on horizontal surface (PV) in Surabaya -East java

Solar radiation is a source of alternative energy that is very influential on the photovoltaic performance in generating energy. The need for solar radiation estimation has become a significant feature in the design of photovoltaic (PV) systems. Recently, the most popular method used to estimate solar radiation is artificial neural network (ANN). However, a new approach, called the extreme learning machine (ELM) algorithm is a new learning method of feed forward neural network with one hidden layer or known as Single Hidden Layer Feed Forward Neural Network (SLFN). In this research, ELM and a multilayer feed-forward network with back propagation are implemented to estimate hourly solar radiation on horizontal surface in Surabaya. In contrast to previous researches, this study has emphasized the use of meteorological data such as temperature, humidity, wind speed, and direction of speed as inputs for ANN and ELM model in estimating solar radiation. The MSE and learning rate has been used to measure the performance of two methods. The simulation results showed that the ELM model built had best performance for 400 nodes in which MSE and learning rate achieved were 5,88e-14 and 0,0156 second, respectively. The values were much smaller compared with the results of ANN. Overall, the ELM provided a better performance.