Path Optimization of Gluing Robot Based on Improved Genetic Algorithm

Abstract

The worn belt surface has acceleration characteristics. Thus, timely and rapid maintenance of the microdamage is vital. To quickly and automatically repair the microdamage is a prime target for the gluing robot (GR).To that end, a new variant Traveling Salesman Problem (TSP) is put forward: according to the worn information and GR's workspace, the worn segments are divided; at a certain worn segment, path optimization of the gluing robot (POGR) problem is presented; then the POGR is simplified into a "double vertices" TSP by Hamilton graph, and the mathematical modeling is built. An improved genetic algorithm (IGA) is proposed to handle the POGR problem, which is called IGA-POGR. The main benefit of the proposed IGA-POGR is the ability to solve POGR of different scales in different ways. The performance of the IGA-POGR is illustrated on four well-known TSP problems and Python simulation is carried out. Numerical results show that IGA-POGR does not give any deviation (0%) from the optimal solution. Compared with discrete particle swarm optimization (DPSO), IGA-POGR has better performance in terms of the solving quality and time consumption when solving four POGR problems.

Application of Improved Genetic Algorithm and Deep Learning in Cold Chain Logistics Distribution Demand Prediction

“…Zhang, Y. Applied fuzzy cognitive map to comprehensively consider the influence of various economic factors on social logistics demand, and determined the influence weight for prediction [12]. Wei, C. Based on the gravity model, forecast regional logistics demand by combining relevant economic theories, mathematical modeling methods, samples, attributes and existing specific problems of regional economic development [13].…”

A Carnivorous Plant Algorithm With Heuristic Decoding Method for Traveling Salesman Problem

“…However, suppose that the cities selected in X ' are 1, 2, 5, and 6, the new route of X ' after reconnection is shown in Fig. 5(d), where d(1, 5) + d (2,6) is 165, d(1, 2) + d (5,6) in X ' is 45, the new route of X ' after reconnection is worse than the initial route. The edges involved in the standard 2opt exchange are chosen at random, and the low probability of excellent individuals is generated, which causes unnecessary search times in iteration.…”

“…As one of the classical discrete combinatorial optimization problems, the TSP, aims to find the shortest route by traveling m cities with minimum distance, each city travels exactly once and can be visited in any order, finally returning to the start city. The practical applications involve logistics distribution [1], AGV path planning [2], UAV route optimization [3], [4], production scheduling [5], [6], and drilling holes in printed circuit boards [7] can be ascribed to TSP. Generally, a minor enhancement of solutions or a reduction in execution time can economize millions of dollars or a significant increase in productivity for enterprises.…”

“…The algorithm which combines these two abilities nicely can refrain itself from converging prematurely in the early stages and quickly converges to the global optimal at the end of optimization. In consequence, meta-heuristic algorithms perform better in TSP with less computation time compared with exact algorithm and heuristic algorithm, it can be summarized into three categories: (1) evolution-based which consists of the genetic algorithm [15], [16]; differential evolution [17]; (2) physics-based which consists of the water cycle algorithm [18], randomized gravitational emulation search algorithm [19]; (3) swarm intelligencebased which consists of ant colony optimization algorithm [20], particle swarm optimization [21], bat algorithm [22], grey wolf optimizer [23], etc.…”

Computer Software Maintenance and Optimization Based on Improved Genetic Algorithm

“…The ability to withstand various threats and disturbances is crucial for upholding the network's integrity and dependability, guaranteeing uninterrupted functionality even in the face of challenging circumstances. By nurturing this flexibility, computer networks can proficiently meet the demands of contemporary digital settings, maintaining an uninterrupted flow of data and information without compromising performance or stability [1]. Mismanagement of network stability can result in equipment malfunctions, severely threatening data preservation and potentially leading to data loss and system immobilization.…”