Evolutionary elements on composite ascent algorithm for multiple response surface optimisation

摘要: Currently, competitive markets place a great emphasis on various quality characteristics to customers. In the past, competition manufacturing of bearing outer rings has primarily focused product hardness. Other stain yield and roundness performance have recently become equally critical fulfill customer satisfaction. To simultaneously meet all requirement criteria, multiple response surface optimisation use desirability function approach combine criteria into single measure determine optimal process design parameters pre-heat heat chamber heaters, number vacuum, gas fan speed in quenching partial pressure. This study proposed integrated algorithms with Taguchi orthogonal analysis forms path composite ascent. There are three phases which conventional aspect steepest ascent via influential parameters, designed for moving toward optiumum, ant colony (ACO) hunting search (HuS) mechanism present getting stuck at local optimum. Results demonstrate that ACO HuS elements superior algorithm average 15.11 16.43 % improvement, respectively, overall responses. The confirmation tests actual based predicted operating conditions were verified carried out show statistically significant improvement 95 confidence interval.