Integrating Process Plan and Part Routing Using Optimization via Simulation Approach

The planning stage of any procedure is critical to its successful and efficient execution. Even in the military, over the last few decades, mission planning support has evolved rapidly using modern Modelling and Simulation (M&S) tools. The article focuses on the M&S of Surface Based Air Defence (SBAD) and the design of the complex hybrid simulator coupling Ordinary Differential Equation (ODE) and Discrete-Event Simulation (DES) models. The simulator includes all entities and procedures that participate in SBAD missions, specifically the ODE models of a target, missile, radar, and the models of Command and Control (C2) system procedures. The design of the simulator also includes the possibilities of automated generation of flight routes, fire control and target distribution for multiple targets and Fire Units (FU) using queuing theory algorithms. As a main platform for the development and scenario design, the Jupyter notebook environment with the Python programming language was used. The primary objectives are to design, validate, and implement the proposed simulator in SBAD mission planning, military cadets' education, and experimental tasks.

Section: Introductionmentioning

confidence: 99%

Coupling of ODE and DES Models for Simulation of Air Defence in War-Gaming Experiment

Stefek¹,

Časar²,

Stary³

et al. 2022

“…Job-shop production control is a classic problem in the combinatory optimization of scheduling rules and production control [1][2][3]. As intelligent and precision manufacturing becomes the trend of industrial production, it is of practical significance to study the job-shop production control.…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning and Rule Scheduling in a Job-Shop Production Control System

Zhao¹,

Zhang²

2021

As intelligent and precision manufacturing becomes the trend of industrial production, it is of practical significance to study the job-shop production control. However, the existing studies have not provided an evaluation mechanism to reasonably measure the control efficiencies of different plans. The desired control objectives are not easily achieved for job-shop production control problems with dynamic changes. Therefore, this paper probes into the dynamic job-shop production control problem based on deep reinforcement learning and rule scheduling. Firstly, a multi-objective optimization model was established for the production control system of dynamic job-shop. Then, deep reinforcement learning was introduced to job-shop production control system to transform the dynamic job-shop production control problem. After that, the authors proposed a dynamic job-shop production control method based on deep reinforcement learning, and explained the collaboration strategy for multiple subsystems. The proposed method was proved effective through experiments.

“…The JSP varies with the conditions of the job-shop. In general, the JSPs can be divided into single-machine JSP [1], parallel-machine JSP [2], open-shop scheduling problem (OSSP) [3], flow-shop scheduling problem (FSSP) [4] and flexible job-shop scheduling problem (FJSP) [5][6][7]. The details of each type of JSP are given in Table I below.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Objective Flexible Job-Shop Scheduling Model Based on Fuzzy Theory and Immune Genetic Algorithm

Shi¹,

Zhang²,

Li³

2020

This paper explores flexible job-shop scheduling problem (FJSP), using the rolling window rescheduling strategy. The fuzzy delivery time was considered, which satisfies the trapezoidal delivery window of the fuzzy membership function and directly bears on consumer satisfaction. Taking machine failure as the cause of dynamic interferences, the author established a dynamic scheduling model for the FJSP with fuzzy delivery time, according to the fuzzy mathematics theory. The model has multiple objectives: minimizing energy consumption, maximum makespan and consumer dissatisfaction. Next, the immune genetic algorithm (IGA) was improved to solve the model. The established model and the improved IGA were verified through simulations, in comparison with the genetic algorithm (GA). The research results shed new light on the FJSPs in real-world scenarios.