Water Saving Control of Turfgrass Irrigation Robot Using Genetic Simulated Annealing Algorithm

Artificial intelligence through the robotic system offers a solution to the quest for an autonomous system with high cutting efficiency for lawn mowing. Because of the current trimming and maintenance operations on grasslands and gardens, it is essential to develop autonomous and efficient lawn pruning electromechanical equipment. This paper describes the design and construction of a high-performance automated grass trimming and irrigating robot. This device cuts and irrigates grass automatically with little human intervention. A genetic simulated annealing algorithm was employed to optimize motor parameters, specifically design a set of mowing mechanisms and mowing height adjustment system. The prototype was tested, which mainly includes the running status evaluation of the walking module, the mowing module, the cutter head lifting module, and the collision detection module. This robot can save water while watering the lawns, reduce labor costs, and improve mowing efficiency. We note that the proposed system can be implemented on a large scale under natural conditions in the future, which will be helpful in robotics applications and cutting grass on lawns and playing grounds.

Hybrid Algorithm Based on Genetic Simulated Annealing Algorithm for Complex Multiproduct Scheduling Problem with Zero-Wait Constraint

Aiming at the complex multiproduct scheduling problem with 0-wait constraint, a hybrid algorithm based on genetic algorithm (GA) and simulated annealing (SA) algorithm was studied. Based on the results of pruning and grading to the operation tree of complex multiproduct, the design structure matrix (DSM) with precedence constraints was established. Then, an initial population coding method based on DSM was proposed and three strategies to optimize the initial population were proposed to improve the quality of the initial population for the situation of multiple operations in the same grade which need to be processed on the same machine. The specific process flow and the setting method of related parameters for the hybrid algorithm were given out. For the infeasible solution produced in the crossover operation, the repair method was proposed. In the decoding process with makespan as the optimization objective, the chromosome genes were classified and the decoding for complex multiproduct scheduling problem with 0-wait constraint was realized through the analysis of its characteristics. The effectiveness of the proposed algorithm for complex multiproduct scheduling problem with 0-wait constraint is verified by the test of related examples in the existing literature.

Fault Localization Based on Hybrid Genetic Simulated Annealing Algorithm

Software testing is an important stage in the software development process, which is the key to ensure software quality and improve software reliability. Software fault localization is the most important part of software testing. In this paper, the fault localization problem is modeled as a combinatorial optimization problem, using the function call path as a starting point. A heuristic search algorithm based on hybrid genetic simulated annealing algorithm is used to locate software defects. Experimental results show that the fault localization method, which combines genetic algorithm, simulated annealing algorithm and function correlation analysis method, has a good effect on single fault localization and multi-fault localization. It greatly reduces the requirement of test case coverage and the burden of the testers, and improves the effect of fault localization.