Modified Self Organizing Neural Network Algorithm for Solving the Vehicle Routing Problem

Author(s):  
Meghan Steinhaus ◽  
Arash Nasrolahi Shirazi ◽  
Manbir Sodhi
Author(s):  
Siyu Zhang ◽  
R. Ganesan ◽  
T. S. Sankar

Abstract The problem of estimating an unknown multivariate function from on-line vibration measurements, for determining the conditions of a machine system and for estimating its service life is considered. This problem is formulated into a multiple-index based trend analysis problem and the corresponding indices for trend analysis are extracted from the on-line vibration data. Selection of these indices is based on the simultaneous consideration of commonly-observed faults or malfunctions in the machine system being monitored. A neural network algorithm that has been developed by the present authors for multiple-index based regression is adapted to perform the trend analysis of a machine system. Applications of this neural network algorithm to the condition monitoring and life estimation of both a bearing system as well as a gearbox are fully demonstrated. The efficiency and computational supremacy of the new algorithm are established through comparing with the performance of Self-Organizing Mapping (SOM) and Constrained Topological Mapping (CTM) algorithms. Further, the usefulness of multiple-index based trend analysis in precisely predicting the condition and service life of a machine system is clearly demonstrated. Using on-line vibration signal to constitute the set of variables for trend analysis, and employing the newly-developed self-organizing neural algorithm for performing the trend analysis, a new approach is developed for machinery monitoring and diagnostics.


2020 ◽  
Vol 49 (2) ◽  
pp. 237-248
Author(s):  
Yuxiang Sheng ◽  
Huawei Ma ◽  
Wei Xia

The vehicle routing problem with task priority and limited resources (VRPTPLR) is a generalized version of the vehicle routing problem (VRP) with multiple task priorities and insufficient vehicle capacities. The objective of this problem is to maximize the total benefits. Compared to the traditional mathematical analysis methods, the pointer neural network proposed in this paper continuously learns the mapping relationship between input nodes and output decision schemes based on the actual distribution conditions. In addition, a global attention mechanism is adopted in the neural network to improve the convergence rate and results. To verify the effectiveness of the method, we model the VRPTPLR and compare the results with those of a genetic algorithm. The parameter sensitivity of each algorithm is assessed using different datasets. Then, comparison experiments with the two algorithms employing optimal parameter configurations are performed for the validation sets, which are generated at different instance scales. It is found that the solution time of the pointer neural network is much shorter than that of the genetic algorithm and that the proposed method provides better solutions for large-scale instances.


Sign in / Sign up

Export Citation Format

Share Document