当前位置: X-MOL 学术Energy Sci. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Optimization of load sharing for parallel compressors using a novel hybrid intelligent algorithm
Energy Science & Engineering ( IF 3.8 ) Pub Date : 2020-10-07 , DOI: 10.1002/ese3.821
Xia Li 1 , Tao Cui 2 , Kun Huang 1 , Xin Ma 3
Affiliation  

Compressor stations, which usually consist of multiple compressors in parallel, are installed to power natural gas travel in pipelines. Compressor station optimization, which should be expressed as a mixed integer nonlinear programming (MINLP) problem, makes economic sense for the entire gas transmission system. However, it has often been simplified as a nonlinear programming (NLP) or mixed integer linear programming (MILP) problem in previous research. Most of existing solutions are based on discretization and a genetic algorithm (GA). This paper addresses the general MINLP problem for compressor station optimization without simplification; a novel hybrid intelligent algorithm is proposed to solve this problem. The proposed algorithm, DWOA, leverages advantages of the whale optimization algorithm (WOA) and differential evolution (DE). The proposed algorithm can balance exploration and exploitation to find the global optimal solution. An approach to handling constraints is also presented, where the original problem model is reformulated to be continuous by expanding the flow rate range of the compressor. A case study is performed to illustrate the performance of this approach. Results show that the continuous reformulated model is easier to solve, and DWOA produces a satisfactory solution that differs from theoretical results by only 1.61%. In addition, DWOA demonstrates better accuracy and stability than WOA, DE, and DE‐WOA, another hybrid algorithm. Therefore, this solution has the potential to promote comprehensive compressor station optimization.

中文翻译:

新型混合智能算法优化并联压缩机的负荷分担

压缩机站通常由并联的多个压缩机组成,用于为管道中的天然气输送提供动力。压缩机站的优化应表示为混合整数非线性规划(MINLP)问题,对整个气体传输系统具有经济意义。但是,在先前的研究中,它通常被简化为非线性规划(NLP)或混合整数线性规划(MILP)问题。现有的大多数解决方案都基于离散化和遗传算法(GA)。本文不加简化地解决了用于压缩机站优化的一般MINLP问题。提出了一种新颖的混合智能算法来解决这个问题。所提出的算法DWOA利用了鲸鱼优化算法(WOA)和差分进化(DE)的优势。所提出的算法可以在探索和开发之间取得平衡,从而找到全局最优解。还提出了一种处理约束的方法,其中通过扩展压缩机的流量范围将原始问题模型重新构造为连续的。进行案例研究以说明此方法的性能。结果表明,连续重构的模型更易于求解,并且DWOA产生了令人满意的解决方案,与理论结果相差仅1.61%。此外,与另一种混合算法WOA,DE和DE-WOA相比,DWOA表现出更好的准确性和稳定性。因此,该解决方案具有促进全面压缩机站优化的潜力。还提出了一种处理约束的方法,其中通过扩展压缩机的流量范围将原始问题模型重新构造为连续的。进行案例研究以说明此方法的性能。结果表明,连续重构的模型更易于求解,并且DWOA产生了令人满意的解决方案,与理论结果相差仅1.61%。此外,与另一种混合算法WOA,DE和DE-WOA相比,DWOA表现出更好的准确性和稳定性。因此,该解决方案具有促进全面压缩机站优化的潜力。还提出了一种处理约束的方法,其中通过扩展压缩机的流量范围将原始问题模型重新构造为连续的。进行案例研究以说明此方法的性能。结果表明,连续重构的模型更易于求解,并且DWOA产生了令人满意的解决方案,与理论结果相差仅1.61%。此外,与另一种混合算法WOA,DE和DE-WOA相比,DWOA表现出更好的准确性和稳定性。因此,该解决方案具有促进全面压缩机站优化的潜力。结果表明,连续重构的模型更易于求解,并且DWOA产生了令人满意的解决方案,与理论结果相差仅1.61%。此外,与另一种混合算法WOA,DE和DE-WOA相比,DWOA表现出更好的准确性和稳定性。因此,该解决方案具有促进全面压缩机站优化的潜力。结果表明,连续重构的模型更易于求解,并且DWOA产生了令人满意的解决方案,与理论结果相差仅1.61%。此外,与另一种混合算法WOA,DE和DE-WOA相比,DWOA表现出更好的准确性和稳定性。因此,该解决方案具有促进全面压缩机站优化的潜力。
更新日期:2020-10-07
down
wechat
bug