A Modified Sine Cosine Algorithm With Teacher Supervision Learning for Global Optimization

The sine cosine algorithm (SCA) is a recently developed meta-heuristic for solving global optimization problems. It has shown excellent performance in algorithms. But this also shortcomings such as low accuracy, easy to fall into local solution, and slow convergence speed. Aiming at these deficiencies of the SCA, modified with teacher supervision learning (TSL-SCA) proposed. First, strategy can guide population accelerate Second, individuals perform reflective after standard SCA position updated, which effectively prevent from stagnating evolutionary process increase diversity. In addition, hybrid inverse method not only enhance ability finding optimal solution distributivity, but balance exploration exploitation capabilities. Differential evolution (DE), particle swarm (PSO), cuckoo search (CS) algorithm, moth-flame (MFO), whale (WOA), Teaching-Learning-Based Optimization (TLBO), TSL-SCA are selected simulation experiment solve 33 benchmark experimental results show that significantly accuracy Furthermore, effectiveness proposed examined by analog circuit fault diagnosis filter examples.