Sparse Array Optimization Method Based on an Improved Genetic Algorithm by Stacking Ensemble Learning

To address the issues of conventional genetic algorithms in sparse array optimization, such as excessive dependence on manual design of fitness functions, a tendency toward premature convergence, and difficulties in balancing multiple constraints during the search process, an improved genetic algorithm based on Stacking ensemble learning for sparse array optimization is proposed in this paper. First, a mathematical model of the sparse array is established, and the mapping relationship of array element topology and beam performance to constraints is constructed by extracting 11-dimensional highly-discriminative multi-domain features from the time domain, frequency domain, wavelet domain, and bispectral domain respectively. Next, a data-driven fitness evaluation method is implemented by designing a Stacking ensemble architecture which involves base learners based on decision trees, support vector machines, and naive Bayes, as well as a meta-learner based on logistic regression. Finally, the above model is integrated into the iterative process of genetic algorithm, forming a closed-loop optimization mechanism that combines ensemble prediction and intelligent search. Multiple sets of simulation results demonstrate that the proposed algorithm exhibits excellent noise-robust performance within an interference-to-noise ratio (INR) range of -10 dB~20 dB, with significant improvements in both sidelobe suppression effect and iterative convergence speed. Compared with the traditional genetic algorithm, the method offers higher optimization accuracy and stronger stability under multi-constraint scenario, providing an efficient and reliable technical solution for the design in radar sparse array engineering.