Flexible Manufacturing System Environment Research Articles

Multi-camera tracking of mechanically thrown objects for automated in-plant logistics by cognitive robots in Industry 4.0

AbstractEmploying cognitive robots, capable of throwing and catching, is a strategy aimed at expediting the logistics process within Industry 4.0’s smart manufacturing plants, specifically for the transportation of small-sized manufacturing parts. Since the flight of mechanically thrown objects is inherently unpredictable, it is crucial for the catching robot to observe the initial trajectory with utmost precision and intelligently forecast the final catching position to ensure accurate real-time grasping. This study utilizes multi-camera tracking to monitor mechanically thrown objects. It involves the creation of a 3D simulation that facilitates controlled mechanical throwing of objects within the internal logistics environment of Industry 4.0. The developed simulation empowers users to define the attributes of the thrown object and capture its trajectory using a simulated pinhole camera, which can be positioned at any desired location and orientation within the in-plant logistics environment of flexible manufacturing systems. The simulation facilitated ample experimentation to be conducted for determining the optimal camera positions for accurately observing the 3D interception positions of a flying object based on its apparent size on the camera’s sensor plane. Subsequently, a variety of calibrated multi-camera setups were experimented while placing cameras at identified optimal positions. Based on the obtained results, the most effective multi-camera configuration setup is derived. Finally, a training dataset is prepared for 3000 simulated throwing experiments where the initial part of the trajectory consists of observed interception positions, through derived best multi-camera setup, and the final part consists of actual positions. The encoder–decoder Bi-LSTM deep neural network is proposed and trained on this dataset. The trained model outperformed the current state-of-the-art by accurately predicting the final 3D catching point, achieving a mean average error of 5 mm and a root-mean-square error of 7 mm in 200 real-world test experiments.

From Nash Q-learning to nash-MADDPG: Advancements in multiagent control for multiproduct flexible manufacturing systems

The emergence of flexible manufacturing systems (FMS) capable of processing multiple product types is a result of the growing demand for product customization and personalization. Such multiproduct systems are characterized by a higher level of uncertainty and variability when compared to traditional manufacturing systems. This paper proposes a Nash integrated multiagent deep deterministic policy gradient method (Nash-MADDPG) to control the mobile robots’ assignment in a multiproduct FMS to enable intelligent decision-making, interaction, and dynamic learning capabilities. A mathematical model of a multiproduct FMS from a previous study is described, and system dynamic property is characterized by permanent production loss (PPL). Then, by observing PPL of the system and market demand for each product type, the multi-agent control scheme is developed to assign mobile robots to load/unload various product types at various machines. First, a Nash game is developed among the mobile robots and to improve the cooperation, a collaboration cost is defined. This collaboration cost is then used in the reward function of the multiagent deep deterministic policy gradient (MADDPG) algorithm. Second, the actions are jointly defined based on the action values of MADDPG, and the mobile robots’ strategies in the Nash game, which update the environment to a new state. The performance of the proposed method is verified by comparing it with conventional Nash Q-learning, vanilla MADDPG, Q-learning based single agent reinforcement learning (SARL) and a first-come-first-serve (FCFS) based control. The results demonstrate that the multi-agent control scheme under the proposed Nash-MADDPG is effective in dealing with cooperative FMS environment that involves complicated dynamics and uncertainties.

Adaptive fuzzy-genetic algorithm operators for solving mobile robot scheduling problem in job-shop FMS environment

Flexible Manufacturing Systems (FMS) is known as one of the recurring themes that possess these promising characteristics with a synergistic combination of productivity-efficiency transport and flexibility through a number of machine tools alongside other material handling devices. In FMS, mobile robots are commonly deployed in material handling system for the purpose of increasing the efficiency and productivity of the manufacturing process. A reliable, efficient, and optimal scheduling is the most important in manufacturing system. The scheduling problems can become highly complex, especially in large-scale systems with numerous tasks and constraints. Thus, schedule optimization becomes crucial to enhance target performance by determining the best allocations and sequences of resources under specified constraints. Recently, Genetic Algorithm (GA) is a remarkably applicable search algorithm to solve scheduling problems to the way that near optimal could be found. While the performance of GA much depends on the selection of the main parameters, a standard GA may suffer from the issue of premature convergence due to the lack of control on its parameters especially crossover and mutation operators. As there is no specific method or way to tune these parameters, the algorithm is prone to converge on the local optimum, thereby leading to performance degradation. To overcome such flaw, this paper proposed an improved Genetic Algorithm using an adaptive Fuzzy Logic to control crossover and mutation operators (FGAOC) for the solution to the NP-hard problem of scheduling mobile robot within Job-Shop FMS environment. The proposed algorithm has been evaluated in several case studies such as small and large-scale problem, various numbers of mobile robots and the 40-test benchmark problem. The results have demonstrated that the proposed FGAOC has delivered a good performance in exploration-exploitation activities with better solution quality.

Genetic Algorithm for Solving Mobile Robot Scheduling Problem in Flexible Manufacturing Environment

The scheduling genuinely a complex process, aimed at optimizing operational activities in pursuit of one or more objectives by leveraging production data which may include previous schedules. The scheduling problem in Flexible Manufacturing System (FMS) is commonly categorized as Nondeterministic Polynomial (NP)-hard combinatorial optimization problems and it remains as an endure problem to industrial practitioners and researchers. As part of real production scheduling, once one task is finished processing on a machine, transportation equipment such as mobile robot transports the completed task to the next machine. The problem of scheduling mobile robot in FMS pertains to the task allocation process for the robots, considering the transportation costs and the time spent to complete all operations. In recent years, Genetic Algorithm (GA) has been a remarkably effective search algorithm for solving a wide range of scheduling problems in a manner that achieves near-optimal solutions. This paper presents the metaheuristic techniques, specifically genetic algorithm, to address the NP-hard scheduling problem of two identical mobile robots in Job-Shop FMS environment. The algorithm is developed with the aim of finding feasible solutions to the integrated problem by minimizing the amount of time it takes to finish all tasks, commonly referred to as makespan. The performance of GA is evaluated with some numerical experiments which is executed via Matlab software. The scheduling results shows that the developed GA able to obtained the near-optimal solution of minimal makespan and converge within a short period of time.

A two-stage heuristic for the sequence-dependent job sequencing and tool switching problem

The job sequencing and tool switching problem is a combinatorial optimization problem that commonly happens in a flexible manufacturing system environment. In this type of environment, a set of flexible manufacturing machines can be configured with various tools to process different jobs and the requirement to switch tools may correspond to a reduction of productivity. Consequently, research on the job sequencing and tool switching problem has been concentrated on minimizing the number of tools switches. This paper discusses the sequence-dependent job sequencing and tool switching problem. The sequence-dependent job sequencing and tool switching problem extends the standard model by considering non-uniform setup times since industrial applications indicate that a tool setup time might be influenced by the previously installed tool at the same magazine slot. A two-stage heuristic procedure is developed here. In the first stage, an adaptive large neighborhood search is deployed for finding the near-optimal job sequence. Then, in the second stage, a combination of the Keep Tool Needed Soonest policy and simulated annealing is proposed for the tooling sub-problem. Comprehensive computational experiments are carried out to demonstrate the efficacy and robustness of the proposed method for solving the sequence-dependent job sequencing and tool switching problem.

Intelligent Design of a Dynamic Facility Layout in the Stochastic Environment of Flexible Manufacturing Systems Considering Routing Flexibility

در این پژوهش، ابتدا یک مدل ریاضی جدید مبتنی بر مدل تخصیص درجه دوم برای طراحی استقرار بهینه تسهیلات در هر دوره از افق برنامه­ریزی زمانی چنددوره­ای مسئله استقرار پویا و تصادفی تسهیلات ارائه می‌­شود. در این مدل، علاوه بر در­نظرگرفتن مسیرهای چندگانه تولید برای قطعات، فرض می­شود که تقاضای محصولات متغیرهای تصادفی مستقل با توزیع نرمال باشند؛ به‌طوری‌که میانگین و واریانس آن­ها از یک دوره زمانی به دوره دیگر به‌طور تصادفی تغییر کند؛ همچنین برای حل مدل ریاضی پیشنهادی، یک الگوریتم ترکیبی فراابتکاری جدید با استفاده از الگوریتم‌­های کرافت و شبیه‌­‌سازی تبرید ارائه می­شود. مدل و الگوریتم ترکیبی پیشنهادی با روش­های طراحی آزمایش، مطالعه موردی واقعی، حل چند مسئله نمونه و انجام تحلیل حساسیت مورد­اعتبارسنجی قرار می­گیرند. نتایج نشان می‌­دهد که الگوریتم ترکیبی پیشنهادی از نظر کیفیت جواب و زمان محاسبه نسبت الگوریتم تبرید شبیه­سازی­شده دارای عملکرد بهتری است؛ همچنین امکان استفاده از مدل پیشنهادی برای طراحی استقرار تسهیلات در محیط­های تصادفی و قطعی سیستم‌­های تولیدی سنتی و مدرن وجود دارد.

A Simulation modelling of scheduling of automated guided vehicle in flexible manufacturing system environment

Automated Guided Vehicles (AGVs) are among the fastest and advanced material handling technology that are utilized in various industrial applications today. They can be overlapped to various other manufacturing and storage system and controlled through an advanced computer control system. Flexible Manufacturing systems (FMS) are compatible for concurrent manufacturing of a good sort of parts in low quantity. The Flexible Manufacturing systems elements can operate in a non parallel manner and the scheduling problems are harder. The use of AGVs is increasing day by day for the fabric movement in production lines of flexible manufacturing plants. The purpose is to extend efficiency in material transfer and increase manufacturing. Though the hardware of Automated Guided Vehicle has made remarkable enhancement in the field but the software control of the speed still lacks in many applications. The order of scheduling of operations on machine centers as well as the scheduling of Automated Guided Vehicles are important factors contributing to the overall efficiency of flexible manufacturing system (FMS). In this work, scheduling of job is done for a particular type of flexible manufacturing system (FMS) environment by using the technique of optimization called the genetic algorithm (GA). A code was developed to seek out the optimal solution and generate random values in Ms-Excel. When a chromosome is input, the GA works upon it and produces same number of offspring’s. The number of iterations takes place until the optimum solution is obtained. Here we've worked upon eight problems, with different no. of machines and no. of jobs. The input parameters used are time period matrix and time interval matrix with the amount of machines and number of jobs. The results obtained are very quite close to the results obtained by other techniques and by other scholars.

A CEGA-Based Optimization Approach for Integrated Designing of a Unidirectional Guide-Path Network and Scheduling of AGVs

In the current industrial fields, automatic guided vehicles (AGVs) are widely employed to constitute the flexible manufacturing system (FMS), owing to their great advantages of routing flexibility and high efficiency. However, one main challenge lies in the coupling process of the design problem of the unidirectional guide-path network (UGN) and the task scheduling problem of AGVs. To reduce the complexity, most pertinent literatures only handle these problems one by one, based on the stepwise design methods, thereby neglecting the constraint conditions and the optimization objectives caused by the FMS environment. The motivation of the paper is to bring the coupling factors into the integrated design and solution process. Firstly, an integrated design model of designing UGN and scheduling AGVs simultaneously is proposed, with the objective of minimizing the makespan (i.e., the maximum completion time of all handling tasks), in the consideration of the practical constraints, e.g., the job handling and processing sequence constraints and the AGV number constraint. Secondly, a dual-population collaborative evolutionary genetic algorithm (CEGA) is developed to solve the problems of designing and scheduling in a parallel way. The solutions of the integrated model, i.e., the potential strongly connected UGN and the feasible processing and handling sequence, are, respectively, coded as two different subpopulations with independent and concurrent evolution processes. The neighbourhood search operation, the niche technique, and the elitism strategy are combined to improve the convergence speed and maintain the population diversity. The experimental results show that the integrated design model can formulate the problem more accurately, and the CEGA algorithm is computationally efficient with high solution quality.

An AHP-based comparison between automated and manual material handling systems in FMS environment

Flexible manufacturing is a process which permits production systems to perform under high customised production needs. The goals of manufacturing systems like minimum inventories, improved quality, enhanced technical performance and reduction of cost can be achieved by implementing the FMS. Material handling system plays a very important role and consumes a significant amount of cost and time in flexible manufacturing system (FMS). Since a lot of factors affect the material handling system, so selection of best suitable material handling system which optimises all these factors is a big problem before any material manager. The purpose of this study is to present a multi-criteria decision making comparison model which would be very useful for choosing better alternative between automated and manual material handling system (MMHS). Analytical hierarchy process (AHP)-based comparison is performed upon these attributes to select the best alternative between manual material handling system and automated material handling system (AMHS).

An AHP based comparison between automated and manual material handling systems in FMS environment

Flexible manufacturing is a process which permits production systems to perform under high customised production needs. The goals of manufacturing systems like minimum inventories, improved quality, enhanced technical performance and reduction of cost can be achieved by implementing the FMS. Material handling system plays a very important role and consumes a significant amount of cost and time in flexible manufacturing system (FMS). Since a lot of factors affect the material handling system, so selection of best suitable material handling system which optimises all these factors is a big problem before any material manager. The purpose of this study is to present a multi-criteria decision making comparison model which would be very useful for choosing better alternative between automated and manual material handling system (MMHS). Analytical hierarchy process (AHP)-based comparison is performed upon these attributes to select the best alternative between manual material handling system and automated material handling system (AMHS).

?A Simulation Study for Investigation of Routing Flexibility on Performance in Flexible Manufacturing System Environment

Background/objectives: Flexible manufacturing is a concept which allows manufacturing under highly customized ­production requirements. The aim of this simulation study is to scrutinize the effect of routing flexibility on the different performance measures in the proposed FMS (Flexible manufacturing systems). Methods/Statistical Analysis: The proposed FMS have been modeled based on the input data and the system parameters using ARENA simulation software. ANOVA has been used for analyzing the simulation results in different manufacturing scenarios. Findings: The developed simulation model aids in better routing of jobs in real manufacturing scenario under breakdown situations. An investigation using simulation results has been made to present the comparative study on flexible routing of jobs in an FMS environment which is subject to unexpected machining area break downs. Using ARENA simulation software the result obtained from the developed model for performance measures have been analyzed. The transfer time has been found more influencing than other factors on the performance of the system. Applications/Improvements: The proposed simulation model aids in improved design, planning and control of jobs and to arrive at judicious types and levels of routing in order to attain an enhanced performance in a complex manufacturing system under the breakdown situations. Keywords: Alternative Routing, ARENA Simulation, Flexible Manufacturing System, Routing Flexibility

A Multi Attribute Selection of Mobile Robot using AHP/M-GRA Technique

Today's highly competitive environment and volatile market conditions at national and international level are forcing the manufacturing concerns and its management to adopt the advance automated material handling equipment like mobile robots in a flexible manufacturing system (FMS) to meet the customers' demand regarding quality and variety of product at minimal cost. Selection of a robot is one of the most difficult problems in today's manufacturing environment. The problem has become more challenging due to increasing specifications and complexity of the robot. The main aim of this paper is to develop and implement an integrated methodology based on AHP (Analytical Hierarchy Process) and M-GRA (Modified Grey Relational Analysis) for the selection of a mobile robot for material handling in FMS environment. In this methodology, AHP technique has been used to assign the relative importance between mobile robot selection attributes and M-GRA technique is applied to determine mobile robot selection utility index. The proposed AHP/M – GRA technique is more suitable for the decision making in the presence of vagueness. The methodology is illustrated by means of an example. The ranking and evaluation of this process will provide a good guidance to the decision maker/user to select the appropriate material handling equipment on the basis of attributes. This is the novel effort in the area of robot selection.

AGV Controlled FMS

One of the key factors that prevent the implementation of Flexible Manufacturing Systems (FMS) is the elaborate cost associated with the control software. In a FMS there is often a wide range of equipment, such as personal computers, Programmable Logical Controllers (PLCs), CNC Machines or robots, each of these having their ownintelligence' and library of data. Providing a means of communication between these individual controllers has traditionally been achieved using a Local Area Network (LAN). This proves more expensive when traditional manual operated machines have to be integrated into the system. The model described in this paper provides an alternative to the con- ventional use of a LAN in a FMS environment. In the design solution, an Automatically Guided Vehicle (AGV) is used as both the materials handling unit and the communications line linking each station to the host controller. Communications between the AGV and peripheral equipment is achieved using a standard infrared data link, eliminating hard-wiring and network protocols. A simulation model has been developed to demonstrate the feasibility of such a system, using industrial data. The software package Witness is used to develop the simulation model. The objective from developing this simulation model is to test whether an AGV is capable of meeting the demands of such a scenario. The research undertaken aims to test this by modelling an existing factory layout. Using this layout and captured machining times and part routes, from the factory database, the feasibility of such AGV controlled production system is established. The model shows that such a system is plausible in a scenario where machine times are high and the distance between machines is large.

Hybrid multiobjective genetic algorithms for integrated dynamic scheduling and routing of jobs and automated-guided vehicle (AGV) in flexible manufacturing systems (FMS) environment

The paper presents an algorithm for integrated scheduling, dispatching, and conflict-free routing of jobs and AGVs in FMS environment using a hybrid genetic algorithm. The algorithm generates an integrated schedule and detail routing paths while optimizing makespan, AGV travel time, and penalty cost due to jobs tardiness and delay as a result of conflict avoidance. The multi-objective fitness function use adaptive weight approach to assign weights to each objective for every generation based on objective improvement performance. Fuzzy expert system is used to control genetic operators using the overall population performance improvements of the last two previous generations. Computational experiments was conducted on the developed algorithm coded in Matlab to test the effectiveness of the algorithm. Integrated scheduling of jobs in FMS which are in synchrony with AGV dispatching, scheduling, and routing proved to ensure the feasibility and effectiveness of all the solutions of the integrated constituent elements.

Mathematical models for FMS loading and part type selection with flexible process plans

The loading problem in flexible manufacturing systems (FMS) consider several different manufacturing settings and objective functions but some crucial aspects of FMS environments, such as flexible process plans (FPP), have not yet received adequate attention. FPPs are vital in coping with bottlenecks and breakdowns, and decreasing the flow time. Modelling FPPs within a loading model, however, increases the problem complexity. In this study, we work on the integrated version of FMS part type selection and loading problems, and propose two models that consider operation allocation at different levels of detail for an FMS with FPP. Operation allocation is modelled explicitly along with tool loading in our first model, while the second one considers it implicitly to obtain a more compact and efficient formulation. Both models show remarkable reduction in run time compared to an existing loading model proposed for a similar FMS environment. [Received 19 August 2012; Revised 15 November 2013; Accepted 21 November 2013]

Scheduling optimization of flexible manufacturing system environment using Differential evolution and Bacterial Foraging Optimization Algorithms

Scheduling optimization of flexible manufacturing system environment using Differential evolution and Bacterial Foraging Optimization Algorithms

Using Genetic Algorithms to solve scheduling problems on flexible manufacturing systems (FMS): a literature survey, classification and analysis

This paper reviews the literature regarding Genetic Algorithms (GAs) applied to flexible manufacturing system (FMS) scheduling. On the basis of this literature review, a classification system is proposed that encompasses 6 main dimensions: FMS type, types of resource constraints, job description, scheduling problem, measure of performance and solution approach. The literature review found 40 papers, which were classified according to these criteria. The literature was analyzed using the proposed classification system, which provides the following results regarding the application of GAs to FMS scheduling: (1) combinations of GAs and other methods were relatively important in the reviewed papers; (2) although most studies deal with complex environments concerning both the routing flexibility and the job complexity, only a minority of papers simultaneously consider the variety of possible capacity constraints on an FMS environment, including pallets and automated guided vehicles; (3) local search is rarely used; (4) makespan is the most widely used measure of performance.

Performance optimization of simultaneous machine and automated guided vehicle scheduling using fuzzy logic controller based genetic algorithm

The current trend in manufacturing technology is considered by two main items automation and flexibility. Flexible manufacturing system (FMS) is one of the most identified systems that include both automation and flexibility criteria. It comprises three principle elements: computer controlled machine tools, an automated material handling system and a computer control system. One of the automated materials handling equipment in FMS is automated guided vehicles (AGVs). Integrated scheduling of AGVs and machines is an essential factor contributing to the efficiency of the manufacturing system in FMS environment. Previously, genetic algorithm (GA) is considered as a heuristic method to solve AGV scheduling problem. GA may not be able to achieve the global optimum due to premature convergence because of control’s lack on its operators parameters. Fuzzy logic controller (FLC) is proposed to control the behavior of GA during solving the scheduling problem of AGVs. This paper presents a job-based GA that is based on job sequencing. Through the optimization, the FLC is used to control the GA operators (crossover and mutation rate) simultaneous to solve the AGV scheduling problem. Key words: Flexible manufacturing system, automated guided vehicle, simultaneous scheduling, genetic algorithm, fuzzy logic controller, optimization.

A review of intelligent approaches for designing dynamic and robust layouts in flexible manufacturing systems

Facility layout problem is associated with the arrangement of facilities in a plant. It is a critical issue in the early stages of designing a manufacturing system because it affects the total manufacturing cost significantly. Dynamic and robust layouts are flexible enough to cope with fluctuations and uncertainties in product demands in volatile environment of flexible manufacturing systems. Since the facility layout is a hard combinatorial optimization problem, intelligent approaches are the most appropriate methods for solving the large size of this problem in reasonable computational time. In this paper, first of all, dynamic and robust layouts are surveyed. After a quick look of different mathematical models, including quadratic assignment, quadratic set covering, mixed integer programming, and graph theoretic models, the various solution methods especially intelligent approaches along with their advantages and disadvantages are surveyed. Finally, after review of hybrid algorithms, the conclusion of this paper is reported.

Intelligent design of a dynamic machine layout in uncertain environment of flexible manufacturing systems

Since Facility Layout Problem (FLP) affects the total manufacturing cost significantly, it can be considered as a critical issue in the early stages of designing Flexible Manufacturing Systems (FMSs), particularly in volatile environments where uncertainty in product demands is inevitable. This paper proposes a new mathematical model by using the Quadratic Assignment Problem formulation for designing an optimal machine layout for each period of a dynamic machine layout problem in FMSs. The product demands are considered as independent normally distributed random variables with known Probability Density Function (PDF), which changes from period to period at random. In this model, the decision maker's defined confidence level is also considered. The confidence level represents the decision maker's attitude about uncertainty in product demands in such a way that it affects the results of the problem significantly. To validate the proposed model, two different size test problems are generated at random. Since the FLP, especially in multi-period case is a hard Combinatorial Optimization Problem (COP), Simulated Annealing (SA) meta-heuristic resolution approach programmed in Matlab is used to solve the mathematical model in a reasonable computational time. Finally, the computational results are evaluated statistically.