Intelligent design of an unconstrained layout for a flexible manufacturing system

Ficko, Mirko; Brezovnik, Simon; Klančnik, Simon; Balič, Jože; Brezočnik, Miran; Pahole, Ivo

doi:10.1016/j.neucom.2009.06.019

Cited by 20 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It consisted in total of 11 workstations [42]. After this evaluation which provided very positive feedback, the system was evaluated with an even bigger problem, consisted of 25 workstations in total [43]. This case proved the usability and capability of the presented system on larger, complex cases.…”

Section: Examplesmentioning

confidence: 96%

Designing a Layout Using the Modified Triangle Method, and Genetic Algorithms

Ficko¹,

Palčić²

2013

Int. j. simul. model.

View full text Add to dashboard Cite

This paper describes the use of genetic algorithms (GA) for solving the facility layout problem (FLP) within manufacturing systems' design. The paper considers a specific heuristic layout planning method, known as the modified triangle method. This method seeks for an optimal layout solution based on the degrees of flows between workstations. The search for an optimal solution is extremely time-consuming and not suitable for larger systems; therefore we have developed a system based on evolutionary computation. Our paper presents a system, based on GA, and the results obtained regarding several numerical cases from the literature. We propose the usage of this system by presenting numerous advantages over other methods of solving FLP for problem representation and evolutionary computation for solution search.

show abstract

Section: Examplesmentioning

confidence: 96%

Designing a Layout Using the Modified Triangle Method, and Genetic Algorithms

Ficko¹,

Palčić²

2013

Int. j. simul. model.

View full text Add to dashboard Cite

show abstract

“…It includes finding the best available values of some objective function, representing the environment. Particle swarm optimization (PSO) is an optimization method, that mimics swarm intelligence, was developed in 1995 by Kennedy and Eberhart [8] and can be adopted to find optimal values in varieties of problems [9]. Algorithm was inspired by a flock of birds, that search for food, which is represented as the optimal value.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Development of a self-optimizing baking system

Berus¹,

Klančnik²,

Ficko³

2018

Adv.Tech&Mat.

Self Cite

View full text Add to dashboard Cite

This study focuses on designing a protocol for optimization of temperature variances inside heating device. Protocol consists of two major parts. First one is the protocol for monitoring temperature distributions and managing heat sources inside an oven. Second part is the optimization scheme, responsible for minimizing the distribution of temperature. Thermocouple J-type sensors are distributed on horizontal plane inside an oven. Digitally operated relay module switch enables heaters manipulation by pulse-width modulation (PWM) signal. Monitoring and operating of the system components is enabled by to data acquisition (DAQ) device and PC, performing the optimization with Particle swarm optimization algorithm. PSO objective function represented as maximum temperature difference recorded by sensors inside heating device is optimized. Included safety protocol serves as an off-switch if temperature inside the oven reaches critical level.

show abstract

“…Floor layout optimisation as a Combinatorial Optimisation Problem is NP-hard, prompting the use of heuristic methods such as evolutionary optimisation and simulated annealing [7]. An original particle swarm optimisation method for intelligent design of unconstrained layouts was proposed by Ficko et al [8].…”

Section: Review Of Related Researchmentioning

confidence: 99%

Optimisation of Machine Layout Using a Force Generated Graph Algorithm and Simulated Annealing

Kanduč¹,

Rodič²

2016

Int. j. simul. model.

View full text Add to dashboard Cite

This paper presents a novel heuristic method for machine layout optimisation, developed in the course of an internal factory logistics optimisation project. The method is developed from a force-directed graph drawing algorithm, and integrates random permutations using simulated annealing to avoid local minima. The method was verified and validated with a discrete event simulation (DES) model of a furniture development factory consisting of 140 machines. The DES model was developed for manufacturing system analysis as well as design and testing of optimisation methods. The main optimisation goal was reduction of transport costs by minimising the total distance the products travel between the machines. The optimisation problem extends the quadratic assignment problem (QAP) by allowing arbitrary granularity of locations, facility sizes and fixed facilities. The resulting method can be used to solve a wider range of problems by altering the optimisation function or adding new feasibility conditions.

show abstract

Intelligent design of an unconstrained layout for a flexible manufacturing system

Cited by 20 publications

References 17 publications

Designing a Layout Using the Modified Triangle Method, and Genetic Algorithms

Designing a Layout Using the Modified Triangle Method, and Genetic Algorithms

Development of a self-optimizing baking system

Optimisation of Machine Layout Using a Force Generated Graph Algorithm and Simulated Annealing

Contact Info

Product

Resources

About