A genetic approach to automate preliminary design of gear drives

Enumerative Optimization Procedure for the Gear Train Optimization Problem of a Two-Speed Dedicated Electric Transmission

“…Mendi et al [18] used a GA with a static penalty function incorporated in the fitness function to minimize the volume of a single-stage gearbox. Gologlu and Zeyveli [19] utilized a GA to minimize the total volume of a two-stage GT, with static and dynamic penalty function methods implemented to handle constraints. They found that the solutions from the implementation of the dynamic penalty function method were generally better than those from the implementation of the static one.…”

“…The results showed that the PSOA and the SAA were more effective and efficient than the GA. However, numerous trials, especially for inexperienced designers, might have to be performed to appropriately determine several parameters for the advanced stochastic methods used in those studies [16][17][18][19][20][21][22][23] since the efficacies of those methods significantly depend on such parameters. Thus, such a requirement might actually increase the total times for those methods to obtain global optima.…”

“…The enumeration technique is preferred to the random methods [12][13][14][15] and the advanced stochastic methods [16][17][18][19][20][21][22][23] because the number of the possible solutions to the 2DET could be well limited considering practical manufacturing requirements and a high-performance computer could scan and evaluate all the candidates efficiently. In addition, multiple criteria are simultaneously optimized for the 2DET using the MMPO to find global optima since the MMPO could well represent the real optimization purposes of designers in an intuitive, reasonable and comprehensive way.…”

Volume optimization of gear trains with spur gears using genetic algorithm

“…Savsani et al [5] described gear train weight optimization comparing various optimization methods to genetic algorithm (GA) result values. Gologlu and Zeyveli [6] performed preliminary design automation through optimization of gear parameters and properties using a GA based approach. Tand and Tseng [7] presented a new mutation operator to adaptive direct mutation that focuses on simplicity, robustness, and efficiency within the context of RCGAs.…”

Automated optimal design of a two-stage helical gear reducer

“…The last two decades have seen an increasing awareness amongst the power transmission design community of the shortfalls of simple trial and error type methods conventionally used to tackle this highly constrained class of design problems and potential replacements have begun to emerge in the shape of expert systems 2 (Ferguson et al [6], Abersek et al [3]), synthesis tools based on spatial grammars (see the Simulated Annealingdriven, grammar based topological gearbox design tool described by Lin et al [10]), particle swarm searches (Ray and Saini, 2001 [13]), algorithms based on the modeling of civilizations and societies (Ray and Liew, 2003 [12]), constrained quasiNewton local searches (see the study by Thompson et al[15] into the fatigue life versus gearing volume tradeoff) and evolutionary algorithms (the work of Li et al [9] on the application of a fuzzy-controlled genetic search to the optimization of a simple reducer model and the study by Gologlu and Zeyveli [7] for recent examples). In fact, the latter category -headlined by genetic algorithms (GAs) -appears to be the direction of choice at present and there are two key reasons for this.…”