Multi-Objective Production and Scheduling Optimization of Offshore Wind Turbine Steel Pipe Piles Based on Improved Hesitant Fuzzy Method

W.l. Wang, Jinchao Xiao, Dongying Feng, Sanxi Wei, Zhongze WangJournal of Marine Science and Engineering 2023 · DOI

TL;DR

This paper tackles the complex multi-objective scheduling problem for offshore wind turbine steel pipe pile (OWTSPP) production. They introduce an "improved Pythagorean hesitant fuzzy method" (IPHFM) to optimize production by considering maximum completion time, machine load, and total completion time simultaneously, achieving significant efficiency gains over traditional methods.

What Problem Does This Paper Address?

The production of offshore wind turbine steel pipe piles (OWTSPP) is a multi-stage process with inherent complexities. Current scheduling practices often rely on empirical methods, which struggle to balance multiple competing objectives like minimizing production time, machine utilization, and overall cost. This can lead to inefficiencies and a lack of adaptability, especially when urgent production needs arise. The paper aims to bridge this gap by developing a more robust and adaptable scheduling optimization method that can effectively handle these multi-objective challenges in a real-world manufacturing context.

Methods

The authors break down the OWTSPP production into two distinct stages: Flexible Flow Shop Scheduling (FFSS) and Open Parallel Shop Scheduling (OPSS). They model these stages using disjunctive graph models to capture critical path and production time information. The core innovation lies in their "improved Pythagorean hesitant fuzzy method" (IPHFM). This method addresses multi-objective optimization by:

  • Augmented Lagrangian Multiplier Method: This technique is used to convert multiple constraints and objective functions into a single, manageable Lagrange objective function.
  • Hesitant Fuzzy Approach: This extends traditional fuzzy logic to handle uncertainty and multiple attribute decision-making more effectively, incorporating vectors, objective functions, and constraints into a multi-dimensional framework.
  • Normalization and Same-Scale Transformation: Objective functions are normalized to a [0, 1] interval and then transformed to a common scale to allow for meaningful comparison and distance calculations.
  • Pareto Front Generation: Algorithms (Simulated Annealing and a Pareto-Front-Algorithm) are employed to identify a set of non-dominated solutions (the Pareto front).
  • TOPSIS Method: The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is used to rank the Pareto optimal solutions and select the best one based on calculated closeness to ideal and negative-ideal solutions.

Datasets

The study utilizes production data for five different types of OWTSPP provided by a heavy industry enterprise. This data includes processing times for various stages of production (SPS, SPC, RP, LW, CW) on different machines. No new benchmark datasets were introduced; rather, real-world production data was adapted and processed for the study.

Key Insights and Ideas

  • Decomposition is Key: Breaking down the complex OWTSPP production into FFSS and OPSS stages simplifies the overall optimization problem.
  • Fuzzy Logic for Uncertainty: Hesitant fuzzy sets provide a powerful framework for dealing with the inherent uncertainties in manufacturing processes and decision-making.
  • Lagrangian Multipliers for Constraint Handling: The augmented Lagrangian method offers an effective way to integrate complex constraints into the optimization objective.
  • Pareto Front for Multi-Objective Trade-offs: Generating a Pareto front allows for the visualization and selection of solutions that represent optimal trade-offs between competing objectives.
  • TOPSIS for Final Selection: TOPSIS provides a systematic way to rank and select the most suitable solution from the Pareto front based on defined criteria.

Key Results

The proposed improved Pythagorean hesitant fuzzy method (IPHFM) demonstrated significant improvements in production efficiency:

  • Small-scale production: Achieved a 15.7% improvement in production efficiency.
  • Large-scale production: Achieved a 22.16% improvement in production efficiency.
  • Specifically, for a small-scale scenario with five OWTSPP, the optimal schedule reduced completion time by 8 hours (from 56h to 48h) compared to the empirical method.
  • For a large-scale scenario with 25 OWTSPP, the optimal schedule reduced completion time by 35 hours (from 201h to 166h).

Limitations and Future Work

The authors acknowledge several limitations and suggest avenues for future research:

  • Solution Filtering: Some potential solutions might be inadvertently eliminated during the screening process, potentially leading to a loss of optimal solutions.
  • Algorithm Superiority: The paper does not fully verify the superiority of the proposed method against other multi-objective algorithms using comprehensive evaluation indicators.
  • More Than Three Objectives: The reliability of the method with more than three objective functions has not been tested in this specific steel pipe pile scheduling example.
  • Future Work: Future research should focus on testing the method with a larger number of objective functions and exploring its performance against other state-of-the-art multi-objective optimization algorithms.

Summary updated

Abstract

This paper investigates the multi-objective optimization problem in the production of offshore wind turbine steel pipe piles (OWTSPP). Considering the particularity of the steel pipe pile production process, it is divided into a flexible flow shop scheduling (FFSS) stage and an open parallel shop scheduling (OPSS) stage, respectively. Mathematical models are established for each stage, and the critical path and production time information are obtained using a disjunctive graph model. Due to the inability of existing empirical scheduling methods to balance production goals, an improved Pythagorean hesitant fuzzy method (IPHFM) is proposed to solve the multi-objective optimization problem in steel pipe pile production. Specifically, the maximum completion time, machine total load, and total completion time are taken as optimization objectives. The improved Lagrange multiplier method with penalty terms is used to handle the constraints and objective functions, and a Lagrange objective function is generated. Then, the Lagrange objective function matrix is obtained by normalization and same-scale processing, and an algorithm is designed to obtain the Pareto front solution set. Finally, this paper compares the optimal scheduling plans under the empirical scheduling method and the improved method. The results show that the improved method can significantly improve production efficiency in both small-scale and large-scale production, with improvements of 15.7% and 22.16%, respectively.
BibTeX
@article{wang2023multi,
  author = {W.L. Wang and Jinchao Xiao and Dongying Feng and Sanxi Wei and Zhongze Wang},
  title = {{Multi-Objective Production and Scheduling Optimization of Offshore Wind Turbine Steel Pipe Piles Based on Improved Hesitant Fuzzy Method}},
  journal = {Journal of Marine Science and Engineering},
  year = {2023},
  doi = {10.3390/jmse11081505},
}
Figure