Optimal sheet metal fixture locating layout by combining radial basis function neural network and bat algorithm

Wang, Zhongqi; Yang, Yuan; Yang, Bo; Kang, Young Jin

doi:10.1177/1687814016681905

Cited by 9 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, most researchers have formulated optimization models of multipoint fixture layouts to achieve the minimum workpiece deformation and computed the deflection under different fixture layouts by the finite element method (FEM). To further solve optimization formulations, many different types of optimization algorithms have been introduced, such as the genetic algorithm [9,10], particle swarm optimization [11], the bat algorithm [12], the nondominated sorting genetic algorithm [13,14], the cuckoo search algorithm [15], and the grey prediction model [16]. All in all, extensive research has been conducted to optimize the fixture layout of thin shell parts by using probability optimization algorithms coupled with FEM.…”

Section: Introductionmentioning

confidence: 99%

Digital Twin-Driven Reconfigurable Fixturing Optimization for Trimming Operation of Aircraft Skins

2022

Aerospace

View full text Add to dashboard Cite

The incomplete constraint induced by multipoint reconfigurable fixturing and the inherently weak rigidity of thin shell parts significantly hinder the stability of flexible fixturing systems. In particular, during the trimming operation, the number of effective locators may change with the progressive separation of the desired shape from that of the blank part, which easily produces the cliff effect (instantaneous dramatic reduction) of the system stiffness. As a result, the location layout becomes a main crux in reality. Regarding this issue, the author herein presents a digital twin-based decision-making methodology to generate reconfigurable fixturing schemes through integrating virtual and physical information. Considering the intrinsic features of the trimming process, such as the time-varying propagation of the system stiffness and the coupling effects of multiattribute process parameters, the hidden Markov model was introduced to cope with reconfigurable fixturing optimization. To achieve fast convergence and seek a feasible solution, local information (where low system rigidity occurs) was extracted and shared to guide the optimization process in a front-running simulation. To demonstrate the presented method, trimming experiments were performed on a large-size compliant workpiece held by a reconfigurable fixturing system that was developed independently by our research group. The experimental results indicate that the proposed method could adaptively iterate out the optimal locating schema and process control reference from the virtual fixturing and trimming simulation to guarantee the time-varying stability of the trimming process in the real world. Clearly, the digital twin-based reconfigurable fixturing planning approach generated a high possibility of building a context-specific, closed-loop decision-making paradigm and allowing the reconfigurable fixturing system to behave in a more adaptable and flexible manner.

show abstract

Section: Introductionmentioning

confidence: 99%

Digital Twin-Driven Reconfigurable Fixturing Optimization for Trimming Operation of Aircraft Skins

2022

Aerospace

View full text Add to dashboard Cite

show abstract

“…Wang et al. 6 proposed a new method that benefits from Bat algorithm to optimize the fixture layout. In this method, the objective function is estimated by a prediction function that is developed by the RBF neural network.…”

Section: Introductionmentioning

confidence: 99%

Multi-objective optimization of auto-body fixture layout based on an ant colony algorithm

Khodabandeh

Saryazdi

Ohadi

2019

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Fixtures are extensively used in many industries such as the car industry, to locate and constrain the sheet part during the assembly stage. Fixture layout affects on deformation of sheet parts. Therefore, fixture layout optimization is crucial to the accuracy and quality of products. In addition, the number of clamps that uses in the fixture is another important factor that must be considered in fixture design. This article presents a novel fixture layout optimization method by combining multi-objective ant colony algorithm (M-ACO) and the finite element method. The proposed method optimizes the fixture layout and the number of clamps simultaneously as a multi-objective problem. An approximation of Pareto frontier is acquired by the proposed method. The fixture layout for the side reinforcement of a car is optimized using the proposed method. The results show that the proposed approach performs effectively to optimize the auto-body fixture layout.

show abstract

“…Lu and Zhao [11] built a back propagation neural network (BPNN) so as to approximate the deformation of SMP under a given fixture layout and then employed GA to find the optimal fixture layout based on the BPNN prediction model. Wang et al [12,13] proposed a radial basis function neural network (RBFNN) prediction model to predict the deformation of SMP and then carried out the follow-up work to search for the optimal fixture layout by integrating RBFNN and bat algorithm to improve the location quality and optimization efficiency. Furthermore, Yang et al [14] presented an integrated method to determine the optimum fixture locating layout to minimize the overall deformation of SMP by combining kriging with cuckoo search algorithm.…”

Section: Introductionmentioning

confidence: 99%

Multiobjective Optimization for Fixture Locating Layout of Sheet Metal Part Using SVR and NSGA‐II

Yang

Wang

Yang

et al. 2017

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Fixture plays a significant role in determining the sheet metal part (SMP) spatial position and restraining its excessive deformation in many manufacturing operations. However, it is still a difficult task to design and optimize SMP fixture locating layout at present because there exist multiple conflicting objectives and excessive computational cost of finite element analysis (FEA) during the optimization process. To this end, a new multiobjective optimization method for SMP fixture locating layout is proposed in this paper based on the support vector regression (SVR) surrogate model and the elitist nondominated sorting genetic algorithm (NSGA-II). By using ABAQUS6 Python script interface, a parametric FEA model is established. And the fixture locating layout is treated as design variables, while the overall deformation and maximum deformation of SMP under external forces are as the multiple objective functions. First, a limited number of training and testing samples are generated by combining Latin hypercube design (LHD) with FEA. Second, two SVR prediction models corresponding to the multiple objectives are established by learning from the limited training samples and are integrated as the multiobjective optimization surrogate model. Third, NSGA-II is applied to determine the Pareto optimal solutions of SMP fixture locating layout. Finally, a multiobjective optimization for fixture locating layout of an aircraft fuselage skin case is conducted to illustrate and verify the proposed method.

show abstract

Optimal sheet metal fixture locating layout by combining radial basis function neural network and bat algorithm

Cited by 9 publications

References 19 publications

Digital Twin-Driven Reconfigurable Fixturing Optimization for Trimming Operation of Aircraft Skins

Digital Twin-Driven Reconfigurable Fixturing Optimization for Trimming Operation of Aircraft Skins

Multi-objective optimization of auto-body fixture layout based on an ant colony algorithm

Multiobjective Optimization for Fixture Locating Layout of Sheet Metal Part Using SVR and NSGA‐II

Contact Info

Product

Resources

About