当前位置: X-MOL 学术Transp. Res. Part B Methodol. › 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.)
A semi-“smart predict then optimize” (semi-SPO) method for efficient ship inspection
Transportation Research Part B: Methodological ( IF 6.8 ) Pub Date : 2020-10-23 , DOI: 10.1016/j.trb.2020.09.014
Ran Yan , Shuaian Wang , Kjetil Fagerholt

Efficient inspection of ships at ports to ensure their compliance with safety and environmental regulations is of vital significance to maritime transportation. Given that maritime authorities often have limited inspection resources, we proposed three two-step approaches that match the inspection resources with the ships, aimed at identifying the most deficiencies (non-compliances with regulations) of the ships. The first approach predicts the number of deficiencies in each deficiency category for each ship and then develops an integer optimization model that assigns the inspectors to the ships to be inspected. The second approach predicts the number of deficiencies each inspector can identify for each ship and then applies an integer optimization model to assign the inspectors to the ships to be inspected. The third approach is a semi-“smart predict then optimize” (semi-SPO) method. It also predicts the number of deficiencies each inspector can identify for each ship and uses the same integer optimization model as the second approach, however, instead of minimizing the mean squared error as in the second approach, it adopts a loss function motivated by the structure of the optimization problem in the second approach. Numerical experiments show that the proposed approaches improve the current inspection efficiency by over 4% regarding the total number of detected deficiencies. Through comprehensive sensitivity analysis, several managerial insights are generated and the robustness of the proposed approaches is validated.



中文翻译:

半“智能预测然后优化”(semi-SPO)方法可进行有效的船舶检查

对港口的船舶进行有效检查以确保其符合安全和环境法规对海上运输至关重要。鉴于海事主管部门通常具有有限的检查资源,我们提出了三种分两步的方法,将检查资源与船舶相匹配,目的是找出最大的缺陷(违反法规)。第一种方法预测每艘船的每个缺陷类别中的缺陷数量,然后开发一个整数优化模型,该模型将检查员分配给要检查的船。第二种方法是预测每个检查员可以识别的每艘船的缺陷数量,然后应用整数优化模型将检查员分配给要检查的船。第三种方法是半“智能预测然后优化”(semi-SPO)方法。它还预测了每个检查员可以识别的每艘船的缺陷数量,并使用与第二种方法相同的整数优化模型,但是,与其采用第二种方法来最小化均方误差,它采用了由结构引起的损失函数第二种方法的优化问题。数值实验表明,对于检测到的缺陷总数,提出的方法将当前检查效率提高了4%以上。通过全面的敏感性分析,可以生成一些管理见解,并且可以验证所提出方法的鲁棒性。它还预测了每个检查员可以识别的每艘船的缺陷数量,并使用与第二种方法相同的整数优化模型,但是,与其采用第二种方法来最小化均方误差,它采用了由结构引起的损失函数第二种方法的优化问题。数值实验表明,对于检测到的缺陷总数,提出的方法将当前检查效率提高了4%以上。通过全面的敏感性分析,可以生成一些管理见解,并且可以验证所提出方法的鲁棒性。它还预测了每个检查员可以识别的每艘船的缺陷数量,并使用与第二种方法相同的整数优化模型,但是,与其采用第二种方法来最小化均方误差,它采用了由结构引起的损失函数第二种方法的优化问题。数值实验表明,对于检测到的缺陷总数,提出的方法将当前检查效率提高了4%以上。通过全面的敏感性分析,可以生成一些管理见解,并且可以验证所提出方法的鲁棒性。在第二种方法中,它采用了由优化问题的结构所激发的损失函数。数值实验表明,对于检测到的缺陷总数,提出的方法将当前检查效率提高了4%以上。通过全面的敏感性分析,可以生成一些管理见解,并且可以验证所提出方法的鲁棒性。在第二种方法中,它采用了由优化问题的结构所激发的损失函数。数值实验表明,对于检测到的缺陷总数,提出的方法将当前检查效率提高了4%以上。通过全面的敏感性分析,可以生成一些管理见解,并且可以验证所提出方法的鲁棒性。

更新日期:2020-10-30
down
wechat
bug