Machining fixture locating and clamping position optimization using genetic algorithms

Optimisation of fixture layout is critical to reduce geometric and form error of the workpiece during the machining process. In this paper the optimal placement of fixture elements (locator and clamp locations) under dynamic conditions is investigated using evolutionary techniques. The application of the newly developed particle swarm optimisation (PSO) algorithm and widely used genetic algorithm (GA) is presented to minimise elastic deformation of the workpiece considering its dynamic response. To improve the performances of GA and PSO, an improved GA (IGA) obtained by basic GA (GA) with sharing and adaptive mutation and an improved PSO (IPSO) obtained by basic PSO (PSO) incorporated into adaptive mutation are developed. ANSYS parametric design language (APDL) of finite element analysis is employed to compute the objective function for a given fixture layout. Three layout optimisation cases derived from the high speed slot milling case are used to test the effectiveness of the GA, IGA, PSO and IPSO based approaches. The comparisons of computational results show that IPSO seems superior to GA, IGA and PSO approaches with respect to the trade-off between global optimisation capability and convergence speed for the presented type problems.

Machining fixture layout optimization using the genetic algorithm

Fixture layout for machining thin-walled structures plays an important role in fixture performance. This work focuses on the optimization design of machining fixture layout including clamp layout and the layout of support heads. A universal optimization methodology that can automatically generate the optimal machining fixture layout is proposed. The optimization of fixture layout is implemented based on the criteria of minimizing maximum deflection of the thin-walled workpiece while remain relatively small torque caused by the clamping tables. An evolutionary algorithm is employed to solve the fixture layout optimization for the optimal solution. The optimal position of the support heads and the layout of clamping tables obtained from this work vary along with the change of cutting force. To validate the proposed optimization methodology, a fixture layout design for a typical thin-walled structure is optimized as an example. The case study demonstrates the application of the proposed approach in the fixture layout design for thin-walled structures, which is beneficial to design an optimal fixture layout.

Optimisation of machining fixture layout under multi-constraints

Fixture design is a critical step in machining. An important aspect of fixture design is the optimization of the fixture, the primary objective being the minimization of workpiece deflection by suitably varying the layout of fixture elements and the clamping forces. Previous methods for fixture design optimization have treated fixture layout and clamping force optimization independently and/or used nonlinear programming methods that yield sub-optimal solutions. This paper deals with application of the genetic algorithm (GA) for fixture layout and clamping force optimization for a compliant workpiece. An iterative algorithm that minimizes the workpiece elastic deformation for the entire cutting process by alternatively varying the fixture layout and clamping force is proposed. It is shown via an example of milling fixture design that this algorithm yields a design that is superior to the result obtained from either fixture layout or clamping force optimization alone.

Fixture layout is an essential factor in intelligent manufacturing in the shipbuilding industry, affecting assembly quality and efficiency. Its optimization has become an urgent problem in the assembly process of compliant parts. Traditional fixture layout depends on workers’ experience, which leads to butt clearance along the assembly interface. Thus, this article proposes a butt clearance control-oriented fixture layout optimization (BCCFLO) methodology. First, a method for calculating the part dimensional variation under the influence of fixture layout and fixture locating error is developed. Then, a constrained multi-objective integer nonlinear programming (CMINP) model is innovatively formulated to optimize the fixture layout. Furthermore, the non-dominated sorting genetic algorithm-II based on Latin hypercube sampling is designed to address the CMINP model. The case study illustrates and validates that the fixture layout achieved by the proposed method could significantly control the butt clearance for large compliant part assembly in the shipbuilding industry.

Fixture Design Optimisation Considering Production Batch of Compliant Non-Ideal Sheet Metal Parts

For auto-body, fixture layout is very important to gravity deformation and dimensional variation of sheet metal assemblies. Conventionally, the satisfying fixture layouts can be generated by global optimization algorithms, such as genetic algorithm (GA), particle swarm optimization (PSO) and social radiation algorithm (SRA), etc. However, it is very difficult to generate the global optimalsolution because the combinations of fixture layouts are enormousand the gravity deformation must be calculated by finite element analysis for sheet metal parts. Therefore, this paper proposes a hybrid algorithm of GAOT (genetic algorithm in optimization toolbox in MATLAB) and RBF-NN(Radial basis function - neural network) to generate the global optimal fixture layouts. In this paper, the fixture locators are selected from a much smaller candidate pool based on filtering methods. The objective function is the gravity deformation of all measurement operations. A hybrid algorithm of GAOT and RBF-NN is used to optimize fixture locating scheme based on MATLAB macro commands of 3DCS, whose optimization process is fully automated. A case of bracketis applied to demonstrate the proposed method in this paper. The results show that the proposedhybridalgorithm can generate better optimal solutions thanthe current optimization methods.

A genetic algorithm for online-scheduling of a multiproduct polymer batch plant

Fixtures are the work-holding devices, widely used in manufacturing, to completely immobilize the workpiece during machining. The position of fixture elements around the workpiece strongly influences the workpiece deformation which in-turn affects the machining accuracy. The workpiece deformation can be minimized by finding the appropriate position for the locators and clamps. Thus, it is necessary to model the complex behavioral relationship that exists in the fixture–workpiece system. In this research paper, response surface methodology is used to model the relationship between position of locators and clamps and maximum deformation of the workpiece during end-milling, and then the developed model has been optimized by genetic algorithm and particle swarm optimization. As the predictive model is being developed by response surface methodology, a huge reduction in computational complexity and time is achieved during the optimization of machining fixture layout. Also, it is evident that the approach which integrates response surface methodology and particle swam optimization produces better results.

Optimization of fixture layout by means of the genetic algorithm

This paper innovates, within the context of preventive maintenance planning, the application of Genetic Algorithm, as a modern powerful optimization tool, in minimum downtime strategies, for optimal part replacement. Therefore, a brief account of Genetic Algorithm is given and a computer program is written to aid the solution of such problems by Genetic Algorithm. Then, the program is used to solve a numerical example, concerning an equipment with Gaussian failure characteristics. The results obtained by Genetic Algorithm and the ordinary methods are compared to show that exactly the same results can be approached by the application of Genetic Algorithm. Genetic Algorithm and maintenance planning, both being subjects of statistical nature, can be combined to provide a vast area of interesting research work and, hence, some guidelines are suggested for further research.

Process parameters optimization is an important problem in numerical control machining, through the analysis of various factors affecting the cutting effect in cutting process, a mathematical model of cutting parameter optimization in NC machining is established and the constraint conditions are also determined in the paper. The article puts forward using genetic algorithm to realize the optimization of mathematical model, and the optimization analysis results are verified in practical processing. The experimental results show that the optimized cutting parameters can satisfy machining requests and improve the cutting efficiency.

A good exploration ability can ensure that the method jumps out of local optimum in multimodal problems and a good exploitation can ensure an algorithm converge faster to global optimum values. So, this paper proposes a new hybrid sperm swarm optimization and genetic algorithm to obtain global optimal solutions termed HSSOGA which is developed based on the concept of balancing the exploration and exploitation capability by merging Sperm Swarm Optimization (SSO), which has a fast convergence rate, and a Genetic Algorithm (GA) that can explore a search domain efficiently. To ensure that the proposed method delivers good performance, it is evaluated with 11 standard test function problems consisting of 5 unimodal and 6 multimodal functions. The proposed HSSOGA set is compared with conventional GA and SSO methods, as well as with several hybrid methods such as Hybrid Firefly and Particle Swarm Optimization (HFPSO), hybrid Simulated Annealing and Genetic Algorithm (SAGA), Hybrid Particle Swarm Optimization and Genetic Algorithm (HFPSO), hybrid Particle Swarm Optimization and Grey Wolf Optimization (PSOGWO), and closely related Hybrid Sperm Swarm Optimization and Gravitational Search Algorithm (HSSOGSA). The results are evaluated in terms of each method’s best fitness, mean, standard deviation, and convergence rates. The numerical experiment results show that HSSOGA has better convergence towards the true global optimum values as compared to the conventional and existing hybrid methods in most unimodal and multimodal test function problems.

The Meta heuristic algorithms are the higher level technique which helps to find the best feasible solution out of all possible solution of an optimization problem. There are various different types of meta heuristic algorithms like Ant Colony Optimization (ACO), Genetic Algorithm, Simulated Annealing, Particle Swarm Optimization, etc. Genetic Algorithm is a search-based optimization technique based on the biological principle of Genetics and adaptation. It is a meta-heuristic approach which is used to solve complex combinatorial problem. The integration of Genetic algorithm with machine learning will be helpful in solving unconstrained and constrained optimization problem. The various genetic operator like selection operator, mutation and cross-over are discussed which will be helpful in knowing how these operators significantly improves State Space search. In this paper the various applications of Genetic algorithms which can be used in machine learning has been discussed. In this paper the author discussed how the significance of Genetic algorithm will be improved while solving complex optimization problem in machine learning. In this paper, flow diagram of Genetic Algorithms has been discussed which will ease the understanding of complex optimization problem like 0–1 Knapsack, Traveling Salesman Problem, etc. In this paper a comparative analysis between traditional algorithm and genetic algorithm has been done on the basis of parameters like flow of control, state space search, Complication, Preconditions, CPU utilization etc. The various limitations of Genetic Algorithms in solving problems with optimal solutions has also been discussed.