Metaheuristic Approaches to Tool Selection Optimisation

2018

The state of a cutting tool is an important factor in any metal cutting process as additional costs in terms of scrapped components, machine tool breakage and unscheduled downtime result from worn tool usage. Therefore, tool wear prediction plays an important role in industry automation for higher productivity and acceptable product quality. Therefore, in order to increase the productivity of turning process, various researches have been made recently for tool wear estimation and classification in turning process. Chip form is one of the most important factors commonly considered in evaluating the performance of machining process. On account of the effect of the progressive tool wear on the shape and geometrical features of produced chip, it is possible to predict some measurable machining outputs such as crater wear. According to experimentally performed researches, cutting speed and cutting time are two extremely effective parameters which contribute to the development of the crat...

International Journal of Engineering, Science and Technology, 2011

Minimization of non-productive time of tool during machining for 2.5 D milling significantly reduces the machining cost. The tool gets retracted and repositioned several times in multi pocket jobs during rough machining which consumes 15 to 30% of total machining time depending on the complexity of job. The automatic CNC program commonly generates contour parallel tool path. Optimization of tool path length during non-productive time can be modeled on Traveling Salesman Problem (TSP) which belongs to family of non-deterministic polynomial (NP) hard problem. In the present work, a Hybrid Genetic Algorithm (HGA) has been proposed to optimize the non-productive tool path in which the initial seed solution is generated by special heuristic and combined with random initial solution generated by simple genetic algorithm (SGA). A defined performance index known as Relative percentage deviation (RPD) has been used for analyzing the results by varying the size of the jobs. From the analysis, it is found that HGA shows superiority over SGA for same computation time limit as the stopping criteria.

Scope and Purpose-Knowledge of optimal cutting parameters for machining operations is required for process planning of metal cutting operations. Numerous nonlinear and non-convex machining models have been developed with the objective of determining optimal cutting conditions. Traditionally these problems have been solved using gradient based algorithms. The purpose of this article includes studying three non gradient based stochastic optimization algorithms to test their efficiency in solving several benchmark machining models. Abstract-Optimal machining conditions are the key to economical machining operations. In this work, some benchmark machining models are evaluated for optimal machining conditions. These machining models are complex because of non-linearities and non-convexity. In this research, we have used Genetic Algorithms and Simulated Annealing as optimization methods for solving the benchmark models. An extension of the Simulated Annealing algorithm, Continuous Simulated Annealing is also used. The results are evaluated and compared with each other as well as with previously published results which used gradient based methods, such as, SUMT (Sequential Unconstrained Minimization Technique), Box's Complex Search, Hill Algorithm (Sequential search technique), GRG (Generalized Reduced Gradient), etc. We conclude that Genetic Algorithms, Simulated Annealing and the Continuous Simulated Annealing which are non-gradient based optimization techniques are reliable and accurate for solving machining optimization problems and offer certain advantages over gradient based methods.

2020

Genetic algorithm is a part of metaheuristic techniques based on the principles of evolution and survival of the fittest. GA’s have been extensively used in optimization in a variety of computing domains including manufacturing and industrial realms. In this paper, the GA is implemented on multi-objective optimization of CNC milling operations, particularly in pocket machining. The milling area is discretized approximated using a square grid where a sequence of grid squares constitutes a milling toolpath. This paper discusses the modeling and implementation of various GA operators such as selection, crossover, mutation, etc. using a suitable fitness function.

2008

As the needs for fast, efficient and high quality production increases, it is important for every company or manufacturing facility to be able to optimize the resources needed. This paper focuses and resolves the problem of best tool selection for a rough milling operation on 3-axis machines, especially for the production of sculptured surfaces. The tool selection methodology is based on a genetic algorithm optimization procedure. The objective of the algorithm is to achieve quicker machining parameters. Direct comparisons between CAM software simulations and real time experiments have been performed to verify the results. Tool type comparison between flat and ball end cutters is also conducted.

Transactions of Famena, 2013

The aim of this paper is to improve CNC programming of machine tools and to minimize the need for human intervention or manual inputs. The proposed optimization method for tool selection is based on a genetic algorithm. Experimental approval is done by using the Matlab environment and it has been shown that the proposed method is useful for the optimization of cutting tool selection. The reason for developing this method is to reduce human resources during the machining process, and at the same time to decrease the cost of the product, to save time and to achieve higher efficiency. This approach is called intelligent way of CNC programming.

Advances in Production Engineering & Management, 2015

Most of CAD/CAM systems lack fully-automated process planning capabilities and depend on semi-automatic capabilities that necessitate the traditional selection of tools and cutting parameters. This paper attempts to determine proper combinations of cutting tools through the generation of tool paths and optimisation of machining parameters using an example of the CNC milling process. Several machining simulations with different combinations of tool sizes were performed using MasterCAM software. Based on these simulations, substantial variations in tool paths were observed for different tool combinations and as such the optimum tool combination could only be obtained arbitrarily. The tool paths derived from machining simulations were used to optimise machining parameters, that is, cutting speed, feed rate and depth of cut with the objective of minimising production time. In this case, an optimisation model was developed as a nonlinear programming problem and solved using extended LINGO nonlinear software. The results show that the subjectivity when selecting cutting tools can be avoided when appropriate tools are chosen alongside with the generation of a tool path within a CAD/CAM system using optimised machining parameters. As a consequence, CNC machine tools could be effectively utilised and the productivity significantly improved at shorter production time and cost.

Proceedings of the International Conference on Business and Engineering Management (ICONBEM 2021)

Sculptured-dies roughing (SDR) has some different objectives that maybe contradicting and therefore needs trade-off among them. Compared to prismatic and rotational shape machining, SDR is more complex considering the sculptured characteristics of machining surface. Layer-by layer approach applied in SDR requires multiple tools selection and determination of the depth of cut for each cutting layer. Those decisions need to be considered in SDR optimization problem. The trade-off between different objectives are required, such as machining residues/cut-off (or coverage) from the roughing process to be traded-off with the machining (roughing) time. This paper presents a stateof-the-art review on cutting layer and cutting tools selection (CLT) by multi-objective optimization for SDR and presents the needs for a trade-off between machining time and cutoff (residual volume) by minimizing machining Time per Volume Coefficient (TVC). The process is conducted simultaneously. A systematic literature review is presented to show the complexity of the geometric related problem, the optimization techniques that have been applied, and the different objectives in SDR, including some multi-objective coverage. Finally, some directions on algorithms for optimizing TVC in TLC problem is presented. Considering the combinatorial problem in CLT, this paper overviews the Multi-Objectives Dynamic Programming approach (MODP) and Metaheuristics Multiple Objective approaches (MOGA etc.) for CLT problem optimization. The results confirm that the optimum tools combination and cutting layer selection could increase SDR efficiency. The paper conclusion discussed recommended metaheuristic approach to trade-off between machining time and residual volume in more complex problem.

Computers in Industry, 2020

The incorporation of technological advances in industry is a must, even for traditional sectors where most companies are SMEs and investments are limited. Technology can be used to increase productivity and the quality of the manufactured product. Drilling is a common procedure in industry. It usually consists of multiple drilling of a flat surface with a tool. Usually the tool is placed on the surface to be drilled at a safe distance and then it makes the drilling in a linear fashion. Optimization of the tool path often involves reducing the movement of the tool to place it over the next point to be drilled, known as airtime. The problem of minimizing airtime for drill paths is highly complex. Most proposals to solve the problem try to adapt it to the formulation of the Traveling Salesman Problem (TSP), in which the objective is to navigate a list of nodes using the minimum global distance. In this paper, the purpose is to provide a solution to the TSP applied to tool path optimization by means of a Discrete version of the Teacher-Learner-Based Optimization (TLBO) algorithm. To improve performance, the algorithm is implemented using a parallel Computer Unified Device Architecture (CUDA) and run on a manycore Graphical Processing Unit (GPU). The results show that the parallel implementation of Discrete TLBO is faster than 9x the sequential implementation.

Journal of Intelligent Manufacturing

Optimization of process planning is considered as the key technology for computer-aided process planning which is a rather complex and difficult procedure. A good process plan of a part is built up based on two elements: (1) the optimized sequence of the operations of the part; and (2) the optimized selection of the machine, cutting tool and Tool Access Direction (TAD) for each operation. In the present work, the process planning is divided into preliminary planning, and secondary/detailed planning. In the preliminary stage, based on the analysis of order and clustering constraints as a compulsive constraint aggregation in operation sequencing and using an intelligent searching strategy, the feasible sequences are generated. Then, in the detailed planning stage, using the genetic algorithm which prunes the initial feasible sequences, the optimized operation sequence and the optimized selection of the machine, cutting tool and TAD for each operation based on optimization constraints as an additive constraint aggregation are obtained. The main contribution of this work is the optimization of sequence of the operations of the part, and optimization of machine selection, cutting tool and TAD for each operation using the intelligent search and genetic algorithm simultaneously.