Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Zixuan, Song, Xiaowei, Zeng, Yujiao, Li, Jie, Nie, Yaling, Zhu, Min, Chen, Jianhua, Wang, Linmin, Xiao, Xin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.17495
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910804381532160
author Zhang, Zixuan
Song, Xiaowei
Zeng, Yujiao
Li, Jie
Nie, Yaling
Zhu, Min
Chen, Jianhua
Wang, Linmin
Xiao, Xin
author_facet Zhang, Zixuan
Song, Xiaowei
Zeng, Yujiao
Li, Jie
Nie, Yaling
Zhu, Min
Chen, Jianhua
Wang, Linmin
Xiao, Xin
contents With the development of artificial intelligence, simulation-based optimization problems, which present a significant challenge in the process systems engineering community, are increasingly being addressed with the surrogate-based framework. In this work, we propose a deterministic algorithm framework based on feasible path sequential quadratic programming for optimizing differentiable machine learning models embedded problems. The proposed framework effectively addresses two key challenges: (i) achieving the computation of first- and second-order derivatives of machine learning models' outputs with respect to inputs; and (ii) by introducing the feasible path method, the massive intermediate variables resulting from the algebraic formulation of machine learning models eliminated. Surrogate models for six test functions and two process simulations were established and optimized. All six test functions were successfully optimized to the global optima, demonstrating the framework's effectiveness. The optimization time for all cases did not exceed 2s, highlighting the efficiency of the algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17495
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feasible Path SQP Algorithm for Simulation-based Optimization Surrogated with Differentiable Machine Learning Models
Zhang, Zixuan
Song, Xiaowei
Zeng, Yujiao
Li, Jie
Nie, Yaling
Zhu, Min
Chen, Jianhua
Wang, Linmin
Xiao, Xin
Optimization and Control
With the development of artificial intelligence, simulation-based optimization problems, which present a significant challenge in the process systems engineering community, are increasingly being addressed with the surrogate-based framework. In this work, we propose a deterministic algorithm framework based on feasible path sequential quadratic programming for optimizing differentiable machine learning models embedded problems. The proposed framework effectively addresses two key challenges: (i) achieving the computation of first- and second-order derivatives of machine learning models' outputs with respect to inputs; and (ii) by introducing the feasible path method, the massive intermediate variables resulting from the algebraic formulation of machine learning models eliminated. Surrogate models for six test functions and two process simulations were established and optimized. All six test functions were successfully optimized to the global optima, demonstrating the framework's effectiveness. The optimization time for all cases did not exceed 2s, highlighting the efficiency of the algorithm.
title Feasible Path SQP Algorithm for Simulation-based Optimization Surrogated with Differentiable Machine Learning Models
topic Optimization and Control
url https://arxiv.org/abs/2501.17495