Highlights Develop a tailored multi-target random forest model for predicting ship deficiencies. Prove that ship inspection planning is polynomially solvable. Proposed approaches outperform the current practice by over 4%.

    Abstract 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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A semi-“smart predict then optimize” (semi-SPO) method for efficient ship inspection


    Beteiligte:
    Yan, Ran (Autor:in) / Wang, Shuaian (Autor:in) / Fagerholt, Kjetil (Autor:in)


    Erscheinungsdatum :

    2020-09-28


    Format / Umfang :

    26 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    A smart predict-then-optimize method for targeted and cost-effective maritime transportation

    Tian, Xuecheng / Yan, Ran / Liu, Yannick et al. | Elsevier | 2023



    A Smart Predict-then-Optimize method for dynamic green bike relocation in the free-floating system

    Chang, Ximing / Wu, Jianjun / Sun, Huijun et al. | Elsevier | 2023


    Semi-submerged ship

    LIU BING / ZHU WANWU / CUI BIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Semi-submerged ship

    HE GUANGYU / XIE DONGWEI / CAI RUIMOU et al. | Europäisches Patentamt | 2022

    Freier Zugriff