Mountain railway alignment optimization using stepwise &amp; hybrid particle swarm optimization incorporating genetic operators

Pu, Hao; Song, Taoran; Schonfeld, Paul; Li, Wei; Zhang, Hong; Hu, Jianping; Peng, Xianbao; Wang, Jie

doi:10.1016/j.asoc.2019.01.051

Cited by 53 publications

(33 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of the least‐cost alignment optimization problem is to find an alignment with the lowest comprehensive cost between start and end points (Jong & Schonfeld, 2003). The cost function used in this study is the same as in our previous publications (Li et al., 2016; Pu, Song, Schonfeld, Li, Zhang, Hu et al., 2019). It contains the following components: Construction cost, including costs spent on bridge construction ( C B ), tunnel construction ( C T ), earthwork construction ( C E ), length‐dependent construction ( C L ), and right‐of‐way expenses ( C R ). Operation cost, which is the sum of annual operating costs related to the deflection angles at HPI's ( C A ), to alignment length ( C M ) and to gradients ( C G ). …”

Section: Least‐cost Railway Alignment Optimization Modelmentioning

confidence: 99%

“…The detailed mathematical formulations for computing the cost components in Equation () can be found in our earlier publications (Li et al., 2016; Pu, Song, Schonfeld, Li, Zhang, Hu et al., 2019) and are not duplicated here.…”

Section: Least‐cost Railway Alignment Optimization Modelmentioning

confidence: 99%

“…Meanwhile, alignment cost is another deciding factor in mountain railway alignment design. That occurs because mountain railway alignments are largely comprised of expensive bridge and tunnel sections (Pu, Song, Schonfeld, Li, Zhang, Hu et al., 2019). It is quite difficult to properly design these expensive constructions without excessive alignment cost.…”

Section: Introductionmentioning

confidence: 99%

“…Then, these paths were used as centerlines to generate a set of railway corridors (Area‐corridor stage). In the next stage (Li et al., 2017; Pu, Song, Schonfeld, Li, Zhang, Hu et al., 2019; H. Zhang et al., 2020), we used a stepwise & hybrid particle swarm optimization‐genetic algorithm (PSO‐GA), which is an evolutionary‐based method for engineering problems (e.g., Adeli & Cheng, 1993, 1994; Adeli & Kumar, 1995a, 1995b; Kociecki & Adeli, 2015; Sarma & Adeli, 2001), to obtain final alignment solutions in specific railway corridors (Corridor‐alignment stage). Although these methods have been verified to be successful for optimizing mountain railway alignments, the aims of both of these optimization processes were to find least‐cost solutions in the search spaces, without accounting for geological hazard factors.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Mountain railway alignment optimization considering geological impacts: A cost‐hazard bi‐objective model

Song

Schonfeld

et al. 2020

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Railways are greatly threatened by geological hazards whose disastrous effects include severe economic losses as well as serious casualties. It is vital to properly account for such geological hazardous impacts during a railway alignment optimization process. However, geological factors are complex, especially in mountainous regions. Besides, economic factors are also crucial in railway alignment design. Therefore, railway alignment optimization can be termed as a cost-hazard bi-objective decision-making process. So far, least-cost railway alignment optimization has been studied quite thoroughly while the complicated geological hazard factors have received relatively little attention. In this study, a bi-objective alignment optimization model considering cost and geological hazard is developed. A novel geological railway alignment optimization model is proposed, which includes spatial geological constraints and geological hazard evaluations, after geological railway alignment design criteria are presented and analyzed for three kinds of typical geological hazards: debris flows, landslides, and rockfalls. The geological hazard evaluation includes geological susceptibility and vulnerability assessments. Then, this model is integrated with a previous least-cost alignment optimization model to construct a cost-hazard bi-objective model. The alignment searching processes are also improved to solve the proposed model by integrating geological-constraints-handling and bi-objective alignment optimization approaches. Finally, the effectiveness of the proposed method is verified by applying it to a complicated real-world case. The results show that the proposed method can produce less expensive and safer solutions than the best alignment designed by experienced human designers while satisfying all required design standards. Moreover, the method's applicability for solving actual problems is further demonstrated through the sensitivity analysis. 1 INTRODUCTION Geological hazards greatly threaten the construction and operation of railways. Their disastrous effects include not

show abstract

Section: Least‐cost Railway Alignment Optimization Modelmentioning

confidence: 99%

Section: Least‐cost Railway Alignment Optimization Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mountain railway alignment optimization considering geological impacts: A cost‐hazard bi‐objective model

Song

Schonfeld

et al. 2020

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…The usual goal of alignment optimization is to find an alignment with the lowest comprehensive cost between two given endpoints. In the literature, representative methods for optimizing alignments include particle swarm optimization (Shafahi & Bagherian, 2013;Babapour, Naghdi, Ghajar, & Mortazavi, 2018;Pu et al, 2019), two-stage method that combines global optimization methods with a gradient type algorithm (Vázquez-Méndez, Casal, Santamarina, & Castro, 2018), derivative-free algorithms (Mondal, Lucet, & Hare, 2015), discrete algorithms (Hirpa, Hare, Lucet, Pushak, & Tesfamariam, 2016;, dynamic programming (Hogan, 1973;Li, Pu, Zhao, & Liu, 2013), mixed integer programming (Easa & Mehmood, 2008), linear programming (Revelle, Whitlatch, & Wright, 1996;Chapra & Canale, 2006), network optimization (Trietsch, 1987a(Trietsch, , 1987b), heuristic neighborhood search with mixed integer programming (Cheng & Lee, 2006;Lee, Tsou, & Liu, 2009), calculus of variations (Howard, Bramnick, & Shaw, 1968), numerical search (Robinson, 1973), enumeration (Easa, 1988), average-end-area method for improving earthwork calculation accuracy from 2D to 3D (Cheng & Jiang, 2013), genetic algorithms (Maji & Jha, 2009, and distance transforms (DTs) (de Smith, 2006;Li et al, 2016;Li et al, 2017;Pu et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

A three‐dimensional distance transform for optimizing constrained mountain railway alignments

Song

Schonfeld

et al. 2019

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Railway alignment optimization is considered one of the most complicated and time‐consuming problems in railway planning and design. It requires searching among the infinite potential alternatives in huge three‐dimensional (3D) search spaces for a near‐optimal alignment, while considering complex constraints and a nonlinear objective function. In mountainous regions, the complex terrain and constructions require additional and more complex constraints than in topographically simpler regions. In this paper, the authors solve this problem with an algorithm based on a 3D distance transform (3D‐DT). Compared with previous two‐dimensional distance transform (2D‐DT) methods developed in this field, the feasible search spaces of 3D‐DT are greatly increased. Consequently, this new method can find more alternatives with higher qualities. In this approach, an erythrocyte‐shaped 3D neighboring mask is developed to narrow local search spaces and speed up the search process. Besides, a stepwise‐backstepping strategy is designed to dynamically determine feasible 3D search spaces and efficiently search the study area. During the 3D‐DT search process, multiple constraints, including geometric, construction, and location constraints, are effectively handled. After the 3D‐DT search, a genetic algorithm is employed to optimize the 3D‐DT paths into final alignments. Finally, this novel approach is applied to an actual case in a complex mountainous region. The comprehensive cost of the best solution generated by 3D‐DT is 16% below a manual solution produced by very experienced human designers. Furthermore, the total number of feasible alternatives found by 3D‐DT is 4.3 times greater than by 2D‐DT. The comprehensive cost of the best 3D‐DT solution is 10% below the best one generated by 2D‐DT.

show abstract

Cognitive spectroscopy for evaluating Chinese black tea grades (Camellia sinensis): near‐infrared spectroscopy and evolutionary algorithms

Ren

Sun

et al. 2020

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDGrading represents an essential criterion for the quality assurance of black tea. The main objectives of the study were to develop a highly robust model for Chinese black tea of seven grades based on cognitive spectroscopy.RESULTSCognitive spectroscopy was proposed to combine near‐infrared spectroscopy (NIRS) with machine learning and evolutionary algorithms, selected feature information from complex spectral data and show the best results without human intervention. The NIRS measuring system was used to obtain the spectra of Chinese black tea samples of seven grades. The spectra acquired were preprocessed by standard normal variate transformation (SNV), multiplicative scatter correction (MSC) and minimum/maximum normalization (MIN/MAX), and the optimal pretreating method was implemented using principal component analysis combined with linear discriminant analysis algorithm. Three feature selection evolutionary algorithms, which were a genetic algorithm (GA), simulated annealing (SA) and particle swarm optimization (PSO), were compared to search the best preprocessed characteristic wavelengths. Cognitive models of Chinese black tea ranks were constructed using extreme learning machine (ELM), K‐nearest neighbor (KNN) and support vector machine (SVM) methods based on the selected characteristic variables. Experimental results revealed that the PSO–SVM model showed the best predictive performance with the correlation coefficients of prediction set (Rp) of 0.9838, the root mean square error of prediction (RMSEP) of 0.0246, and the correct discriminant rate (CDR) of 98.70%. The extracted feature wavelengths were only occupying 0.18% of the origin.CONCLUSIONThe overall results demonstrated that cognitive spectroscopy could be utilized as a rapid strategy to identify Chinese black tea grades. © 2020 Society of Chemical Industry

show abstract

Mountain railway alignment optimization using stepwise & hybrid particle swarm optimization incorporating genetic operators

Cited by 53 publications

References 34 publications

Mountain railway alignment optimization considering geological impacts: A cost‐hazard bi‐objective model

Mountain railway alignment optimization considering geological impacts: A cost‐hazard bi‐objective model

A three‐dimensional distance transform for optimizing constrained mountain railway alignments

Cognitive spectroscopy for evaluating Chinese black tea grades (Camellia sinensis): near‐infrared spectroscopy and evolutionary algorithms

Contact Info

Product

Resources

About