Optimization of multi-pass turning using particle swarm intelligence

This paper proposes a methodology for selecting optimum machining parameters in multi-pass turning using particle swarm intelligence. Often, multi-pass turning operations are designed to satisfy several practical cutting constraints in order to achieve the overall objective, such as production cost or machining time. Compared with the standard handbook approach, computer-aided optimization procedures provide rapid and accurate solutions in selecting the cutting parameters. In this paper, a non-conventional optimization technique known as particle swarm optimization (PSO) is implemented to obtain the set of cutting parameters that minimize unit production cost subject to practical constraints. The dynamic objective function approach adopted in the paper resolves a complex, multi-constrained, nonlinear turning model into a single, unconstrained objective problem. The best solution in each generation is obtained by comparing the unit production cost and the total non-dimensional constraint violation among all of the particles. The methodology is illustrated with examples of bar turning and a component of continuous form.     

Development of a hybrid particle swarm optimization algorithm for multi-pass roller grinding process optimization

In the field of metal rolling, the quality of steel roller’s surface is significant for the final rolling products, e.g., metal sheets or foils. The surface roughness of steel rollers must fall into a stringent range to guarantee the proper rolling force between the sheet and the roller. To achieve the surface roughness requirement, multiple grinding passes have to be implemented. The current process parameter design for multi-pass roller grinding mainly relies on the knowledge of the experienced engineers. This always requires time tedious “trial and error” and is insufficient to work out cases: (1) multi-pass with complex interaction for one pass with its neighboring passes; (2) large number of process parameters setup; (3) multiple process objectives and constrains. In this paper, a process planning method for multi-objective optimization is proposed with a hybrid particle swarm optimization while incorporating the response surface model of the surface roughness evolution. The hybrid particle swarm optimization regards the entire grinding process parameters (from rough grinding, semi-finish grinding, finish grinding to spark-out grinding) as a whole, and realizes the parameter optimization by considering multiple objectives and constrains. The establishment of the response surface model of surface roughness evolution is capable to incorporate the inter-correlation of neighboring passes into the multi-pass parameter optimization. Finally, the experimental verification was implemented to verify the effectiveness of the proposed method. The error between predicted roughness and experimental roughness is less than 16.53%, and the grinding efficiency is improved by 17.00% compared with the empirical optimal process parameters.     

Optimization of multi-pass face milling using a fuzzy particle swarm optimization algorithm

In this paper, a simple methodology to distribute the total stock removal in each of the rough passes and the final finish pass and a fuzzy particle swarm optimization (FPSO) algorithm based on fuzzy velocity updating strategy to optimize the machining parameters are proposed and implemented for multi-pass face milling. The optimum value of machining parameters including number of passes, depth of cut in each pass, speed, and feed is obtained to achieve minimum production cost while considering technological constraints such as allowable machine power, machining force, machining speed, tool life, feed rate, and surface roughness. The proposed FPSO algorithm is first tested on few benchmark problems taken from the literature. Upon achieving good results for test cases, the algorithm was employed to two illustrative case studies of multi-pass face milling. Significant improvement is also obtained in comparison to the results reported in the literatures, which reveals that the proposed methodology for distribution of the total stock removal in each of passes is effective, and the proposed FPSO algorithm does not have any difficulty in converging towards the true optimum. From the given results, the proposed schemes may be a promising tool for the optimization of machining parameters.     

Multi-objective optimization of multi-pass face milling using particle swarm intelligence

In this paper, to facilitate manufacturing engineers have more control on the machining operations, the optimization issue of machining parameters is handled as a multi-objective optimization problem. The optimization strategy is to simultaneously minimize production time and cost and maximize profit rate meanwhile subject to satisfying the constraints on the machine power, cutting force, machining speed, feed rate, and surface roughness. An efficient fuzzy global and personal best-mechanism-based multi-objective particle swarm optimization (F-MOPSO) to optimize the machining parameters is developed to solve such a multi-objective optimization problem in optimization of multi-pass face milling. The proposed F-MOPSO algorithm is first tested on several benchmark problems taken from the literature and evaluated with standard performance metrics. It is found that the F-MOPSO does not have any difficulty in achieving well-spread Pareto optimal solutions with good convergence to true Pareto optimal front for multi-objective optimization problems. Upon achieving good results for test cases, the algorithm was employed to a case study of multi-pass face milling. Significant improvement is indeed obtained in comparison to the results reported in the literatures. The proposed scheme may be effectively employed to the optimization of machining parameters for multi-pass face milling operations to obtain efficient solutions.     

Optimization of multi-pass turning operations using hybrid teaching learning-based approach

This paper presents a novel hybrid optimization approach based on teaching–learning based optimization (TLBO) algorithm and Taguchi’s method. The purpose of the present research is to develop a new optimization approach to solve optimization problems in the manufacturing area. This research is the first application of the TLBO to the optimization of turning operations in the literature The proposed hybrid approach is applied to two case studies for multi-pass turning operations to show its effectiveness in machining operations. The results obtained by the proposed approach for the case studies are compared with those of particle swarm optimization algorithm, hybrid genetic algorithm, scatter search algorithm, genetic algorithm and integration of simulated annealing, and Hooke–Jeeves patter search.     

Optimization of depth of cut in multi-pass turning using nontraditional optimization techniques

Examining the economics of multi-pass machining operations has significant practical importance. Traditional optimization techniques have been used, but are limited in application. Non-traditional optimization techniques like genetic algorithms, simulated Annealing and ant colony optimization are increasingly used to solve optimization problems. This paper discusses the use of non-traditional optimization techniques for optimizing the depth of cut in multi-pass turning. The resulting subdivision of the cut depth indicates the proposed methodologies are competent, efficient and accurate.     

Multi-objective optimization for surface grinding process using a hybrid particle swarm optimization algorithm

Optimization for the surface grinding process is a problem with high complexity and nonlinearity. Hence, evolutionary algorithms are needed to apply to get the optimum solution of the problem instead of the traditional optimization algorithms. In this work, a hybrid particle swarm optimization (HPSO) algorithm which combines the dynamic neighborhood particle swarm optimization (DN-PSO) algorithm with the strategy of mutation considering constraints is presented to handle multi-objective optimization for surface grinding process. Such four process parameters as wheel speed, workpiece speed, depth of dressing, and lead of dressing are considered as the variables for optimization, and the following three objectives such as production cost, production rate, and surface roughness are used in a multi-objective function model with a weighted approach. Meanwhile, the constraints of thermal damage, wheel wear, and machine tool stiffness are considered. Computational experiments are conducted on cases of both rough grinding and finish grinding, and comparison results with the previously published results obtained by using other optimization techniques shows the efficiency of the proposed algorithm.     

A hybrid unscented filtering and particle swarm optimization technique for harmonic analysis of nonstationary signals

This paper presents a modified unscented Kalman filter for accurate estimation of frequency and harmonic components of a time-varying signal embedded in noise with low signal-to-noise ratio. Further, the model and measurement error covariances along with the unscented Kalman filter parameters are selected using a modified particle swarm optimization algorithm. To circumvent the problem of premature convergence and local minima, a dynamically varying inertia weight based on the variance of the population fitness is used. This results in a better local and global searching ability of the particles, which improves the convergence of the velocity and better accuracy of the unscented Kalman filter parameters. Various simulation results for nonstationary sinusoidal signals with time varying amplitude, phase and harmonic content corrupted with noise, reveal significant improvement in noise rejection and speed of convergence and accuracy in comparison to the well known extended Kalman filter.     

Multi-objective optimization for turning processes using neural network modeling and dynamic-neighborhood particle swarm optimization

In this paper, we introduce a procedure to formulate and solve optimization problems for multiple and conflicting objectives that may exist in turning processes. Advanced turning processes, such as hard turning, demand the use of advanced tools with specially prepared cutting edges. It is also evident from a large number of experimental works that the tool geometry and selected machining parameters have complex relations with the tool life and the roughness and integrity of the finished surfaces. The non-linear relations between the machining parameters including tool geometry and the performance measure of interest can be obtained by neural networks using experimental data. The neural network models can be used in defining objective functions. In this study, dynamic-neighborhood particle swarm optimization (DN-PSO) methodology is used to handle multi-objective optimization problems existing in turning process planning. The objective is to obtain a group of optimal process parameters for each of three different case studies presented in this paper. The case studies considered in this study are: minimizing surface roughness values and maximizing the productivity, maximizing tool life and material removal rate, and minimizing machining induced stresses on the surface and minimizing surface roughness. The optimum cutting conditions for each case study can be selected from calculated Pareto-optimal fronts by the user according to production planning requirements. The results indicate that the proposed methodology which makes use of dynamic-neighborhood particle swarm approach for solving the multi-objective optimization problems with conflicting objectives is both effective and efficient, and can be utilized in solving complex turning optimization problems and adds intelligence in production planning process.     

基于粒子群—遗传混合算法的装配操作优化

为通过装配工艺优化提高车身装配尺寸质量,针对车身众多几何可行装配顺序,应用多属性有向图描述零件间的优先关系和装配控制特征数量,来去除非工程可行装配顺序。以装配尺寸质量为目标函数,提出粒子群—遗传混合算法优化零件间装配操作,通过线性装配偏差分析模型进行装配偏差累积运算,获得了最优装配顺序。通过车身侧围装配体阐述了装配控制特征的优化过程,结果表明,不同的装配顺序将影响装配控制特征的选择,从而影响最终的产品装配偏差。     

Parameter optimization of laser die-surface hardening using the particle swarm optimization technique

A method of multiple-objective optimization is proposed for parameter designing of laser die-surface hardening. The mechanical properties (wear resistance and hardness) and the geometrical properties (hardening depth and surface roughness), which control the hardening effect, are taken as the optimization objectives. A regression analysis is applied to build a non-linear equation for mapping the hardening parameters to the optimization objectives. Multiple constraints are analysed and a model of non-linear multi-objectives is established to optimize the parameters of laser die-surface hardening. The particle swarm optimization (PSO) technique is used for solving this optimization problem. The objectives are contradictive, since the laser die-surface hardening increases the surface hardness of the die, but increases the surface roughness as well. To overcome this problem, the surface roughness is set not only as an objective, but also as a constraint, so that a special fitness function is designed for the iteration of the optimal solution. The die of an auto body is used as an example to test the optimization of parameters. The optimization results show that the optimal parameters can be obtained using this method for laser die-surface hardening which satisfy the hardening requirement, and reduce the hardening time and cost.     

A hybrid particle swarm optimization for parallel machine total tardiness scheduling

The parallel machine scheduling problem has received increasing attention in recent years. This research considers the problem of scheduling jobs on parallel machines with a total tardiness objective. In the view of its non-deterministic polynomial-time hard nature, the particle swarm optimization (PSO), which is inspired by the swarming or collaborative behavior of biological populations, is employed to solve the parallel machine total tardiness problem (PMTP). Since it is very hard to directly apply standard PSO to this problem, a new solution representation is designed based on real number encoding, which can conveniently convert the job sequences of PMTP to continuous position values. Moreover, in order to enhance the performance of PSO, we introduce clonal selection algorithm (CSA) into PSO and therefore propose a new CSPSO method. The incorporation of CSA can greatly improve the swarm diversity and avoid premature convergence. We further investigate three parameters of PSO and CSPSO, finding that the parameters have marginal impact on CSPSO, which indicates that CSPSO is a very stable and robust method. The performance of CSPSO is evaluated in comparison with traditional genetic algorithm (GA) and standard PSO on 250 benchmark instances. Experimental results show that CSPSO significantly outperforms GA and PSO, with obtaining the optimal solutions of 237 instances. Additionally, PSO appears more effective than GA.     

A hybrid particle swarm optimization approach for the job-shop scheduling problem

Managing multiple projects is a complex task. It involves the integration of varieties of resources and schedules. The researchers have proposed many tools and techniques for single project scheduling. Mathematical programming and heuristics are limited in application. In recent years non-traditional techniques are attempted for scheduling. This paper proposes the use of a heuristic and a genetic algorithm for scheduling a multi-project environment with an objective to minimize the makespan of the projects. The proposed method is validated with numerical examples and is found competent.     

An effective hybrid particle swarm optimization for no-wait flow shop scheduling

The no-wait flow shop scheduling that requires jobs to be processed without interruption between consecutive machines is a typical NP-hard combinatorial optimization problem, and represents an important area in production scheduling. This paper proposes an effective hybrid algorithm based on particle swarm optimization (PSO) for no-wait flow shop scheduling with the criterion to minimize the maximum completion time (makespan). In the algorithm, a novel encoding scheme based on random key representation is developed, and an efficient population initialization, an effective local search based on the Nawaz-Enscore-Ham (NEH) heuristic, as well as a local search based on simulated annealing (SA) with an adaptive meta-Lamarckian learning strategy are proposed and incorporated into PSO. Simulation results based on well-known benchmarks and comparisons with some existing algorithms demonstrate the effectiveness of the proposed hybrid algorithm.     

No-idle permutation flow shop scheduling based on a hybrid discrete particle swarm optimization algorithm

A novel hybrid discrete particle swarm optimization (HDPSO) algorithm is proposed in this paper to solve the no-idle permutation flow shop scheduling problems with the criterion to minimize the maximum completion time (makespan). Firstly, two simple approaches are presented to calculate the makespan of a job permutation. Secondly, a speed-up method is proposed to evaluate the whole insert neighborhood of a job permutation with (n?1)² neighbors in time O(mn ²), where n and m denote the number of jobs and machines, respectively. Thirdly, a discrete particle swarm optimization (DPSO) algorithm based on permutation representation and a local search algorithm based on the insert neighborhood are fused to enhance the searching ability and to balance the exploration and exploitation. Then, computational simulation results based on the well-known benchmarks and statistical performance comparisons are provided. It is concluded that the proposed HDPSO algorithm is not only superior to two recently published heuristics, the improved greedy (IG) heuristic and Kalczynski–Kamburowski (KK) heuristic, in terms of searching quality, but also superior to the single DPSO algorithm and the PSO algorithm with variable neighborhood search (PSOvns) in terms of searching quality, robustness and efficiency.     

改进粒子群算法在网格资源分配中的优化

针对并行网格任务的资源分配问题,提出了一种基于并行粒子子群优化的分配算法.该算法引入效用函数,反映网格任务的偏好和目标,利用乘子法转化约束条件,导出适应度函数.最后通过粒子子群的并行寻优过程,得到资源分配的最优解.仿真实验表明了该算法的有效性,且在任务较多的情况下,优化结果好于传统粒子群算法.     

有效的混合粒子群算法求解阻塞流水车间调度问题

针对以最小化完工时间为目标的阻塞流水车间调度问题,提出了一种混合粒子群算法进行求解。该算法将粒子群算法与迭代贪婪算法进行了结合。利用改进的迭代贪婪算法产生问题初始优化解,利用粒子群算法进行全局优化。针对粒子群算法易早熟收敛的特点,提出一种判断粒子停滞和粒子群早熟的方法,并在发现种群早熟后利用迭代贪婪算法的构造操作和毁坏操作对相关粒子进行变异,同时按照一定比例对最差的部分粒子进行重新初始化,以增加种群多样性。通过标准实例测试,验证了所提算法的有效性。     

混合粒子群优化的多小波相邻系数法及其应用

针对传统多小波相邻系数去噪法沿用统一阈值方法获取的阈值精度不高而导致信号去噪不理想的问题,提出了基于混合粒子群优化的多小波相邻系数去噪方法.该方法将具有全局寻优能力的禁忌搜索算法和粒子群优化算法相融合,并将这种融合算法引入到多小波相邻系数去噪方法之中对其阈值求取方式进行改进.通过对比传统的多小波相邻系数去噪方法、基于经...     

应用改进的粒子群优化模糊聚类实现点云数据的区域分割

为实现点云数据的区域划分,提出一种基于改进的粒子群优化与模糊C-均值聚类的混合算法(SPSO-FCM算法)。针对在点云聚类过程中易过早捕获局部极小值的问题,算法首先用改进的粒子群算法——社会粒子群优化算法,对种群进行初始化,通过为每一个粒子设置不同的跟随阈值,来维护种群中个体多样性,加深对种群全局搜索的程度,避免陷入局部极小值;随后,设置种群中每个粒子当前最优位置和初始种群的最优位置,更新自由粒子的位置和跟随粒子的速度和位置;最后,采用模糊C-均值聚类算法求解隶属度矩阵,确定适应值函数,更新所有粒子的最优位置,并判断粒子和种群的位置优越性,得到准确的聚类中心,实现对点云数据的区域划分。以曲面复杂度不一致的点云模型为例对算法进行验证,探讨SPSO-FCM聚类算法的可行性,并与FCM聚类算法、遗传FCM聚类算法进行比对。实验结果显示,SPSOFCM聚类算法较其它两种算法,收敛速度快,迭代次数少,聚类准确,边界区域分割清晰,特别是对型面复杂、点云数据较多的机械零部件点云数据进行分割时,能得到更好的分割结果。