Solving the production transportation problem via a deterministic annealing neural network method
作者：
Highlights：
• Develop a deterministic annealing neural network method based on Lagrange-barrier functions and two neural network models to solve the production transportation problem.
• Apply the Lagrange function to deal with the linear equality constraints.
• Apply the barrier function to make the solution arrives at the near-global or global optimal solution.
• Propose an iterative procedure to optimize the proposed neural network.
• Prove the convergence of the deterministic annealing neural network method to the stable equilibrium state.
摘要
•Develop a deterministic annealing neural network method based on Lagrange-barrier functions and two neural network models to solve the production transportation problem.•Apply the Lagrange function to deal with the linear equality constraints.•Apply the barrier function to make the solution arrives at the near-global or global optimal solution.•Propose an iterative procedure to optimize the proposed neural network.•Prove the convergence of the deterministic annealing neural network method to the stable equilibrium state.
论文关键词：Neural network,Production transportation problem,Deterministic annealing,Combinatorial optimization,Lagrange function
论文评审过程：Received 30 January 2021, Revised 22 June 2021, Accepted 6 July 2021, Available online 20 July 2021, Version of Record 20 July 2021.
论文官网地址：https://doi.org/10.1016/j.amc.2021.126518
