Efficient optimization of engineering problems with a particular focus on high-order iir modeling for system identification using modified dandelion optimizer

Abstract

This paper introduces the modified dandelion optimizer (mDO), a novel adaptive metaheuristic algorithm designed to address complex engineering optimization challenges, with a focus on infinite impulse response (IIR) system identification. The proposed mDO incorporates three key advancements: an enhanced descending phase to improve global exploration, a novel exploration-exploitation phase that balances search intensity and breadth, and a self-adaptive crossover operator that refines solutions dynamically. These innovations specifically target the challenges associated with high-order IIR modeling, enabling mDO to deliver more precise and efficient system identification. To validate its performance, mDO was rigorously evaluated across diverse testing environments, including the CEC2017 and CEC2022 benchmark functions, various IIR model identification scenarios, and real-world engineering design problems such as multi-product batch plant design, multiple disk clutch brake design, and speed reducer design. Comparative analyses reveal that mDO consistently outperforms leading optimization algorithms in terms of accuracy, robustness, and computational efficiency, particularly in complex, high-dimensional landscapes. Statistical assessments further confirm mDO's superior capability in accurately identifying IIR system parameters even under noise and varying model orders. This study positions mDO as a competitive and versatile tool for engineering applications, offering significant improvements in optimization accuracy and adaptability for advanced system modeling and real-world problem-solving.