Time series importance measure-based reliability optimization for cellular manufacturing systems

In industrial engineering, the reliability analysis, modeling and optimization for complex systems are very important. Although the works about reliability optimization with the traditional method are numerous, researchers still study more efficient and accurate methods to solve these reliability problems. The common cause failures are the multiple failures with a common cause, which is typical and serious in practical systems. Therefore, on the basis of normal optimization methods of system reliability, this paper proposes an optimization method of system with common cause failures based on importance measures. The optimization models of parallel system and the series-parallel system are built and are solved with hybrid genetic algorithm. By analyzing the system reliability and cost increasing, the proposed method gives the more accurate, valid and robust optimization results. Meanwhile, the method provides an idea for the reliability optimization of multistate systems.

This paper presents a methodology to solve the manufacturing cell creation and the production scheduling problems for designing virtual cellular manufacturing systems (VCMSs). The objective is to minimize the total materials and components travelling distance incurred. The methodology consists of (i) a mathematical model that describes the characteristics of a VCMS and includes constraints such as delivery due dates of products, maximum capacities of resources, critical tools limitation, and (ii) an ant colony optimization (ACO) algorithm for manufacturing cell formation and production scheduling. Since the proposed ACO algorithm does not indicate a feasible schedule explicitly, two simple heuristics are developed to assign workstations to the operations of the jobs, and to construct the final schedule. To demonstrate the effectiveness of the proposed methodology, both the ACO algorithm and the genetic algorithm are applied to design manufacturing cells for a company in China producing internal combustion engine components. Comparison of the results obtained with the results supplied by the company on the existing manufacturing system show that both the ACO algorithm and the genetic algorithm together with the virtual cellular manufacturing concept perform better than the current manufacturing practice in terms of average workstation utilization, product completion time and system throughput. Also, the results of a set of randomly generated numerical experiments show that the proposed ACO algorithm generates excellent final solutions in a much shorter computation time when compared with the genetic algorithm. Therefore, the mathematical model and the ACO algorithm proposed in this paper form a simple, but effective and efficient methodology to solve the manufacturing cell creation and production scheduling problems for designing VCMSs.

Reliability optimization using ant colony algorithm under performance and cost constraints

The system reliability which applies redundant style of reservoir is studied aiming at the fuzziness of reliability parameter. Firstly, fuzzy chance constrained model of redundant system reliability optimization is given. Then the solution strategy of ant colonies algorithm with fuzzy simulated is studied, and the detailed steps of hybrid intelligent algorithm is given. At last, an instance is given, a reservoir system which has four parts (stages) is solved by ant colonies algorithm with fuzzy simulated, the feasibility of ant colonies hybrid intelligence algorithm with fuzzy simulated is verified by the result of calculation.

Reliability optimization involves the simultaneous evaluation and selection of components and a system‐level design configuration that collectively meets all design constraints, and at the same time, optimizes some objective function, often system reliability or availability. Often these problems are very constrained because of physical or budgetary limitations. There are several variations of reliability optimization and there have been many attempts to determine optimal design configurations for different problem formulations. Applicable optimization methods include dynamic programming, integer programming, mixed integer and nonlinear programming, and metaheuristics, e.g., genetic algorithms (GA). Notable extensions to this problem include multistate reliability optimization and multiple‐objective system reliability optimization.

Seeking multiple optima simultaneously, which multimodal optimization aims at, has attracted increasing attention but remains challenging. Taking advantage of ant colony optimization (ACO) algorithms in preserving high diversity, this paper intends to extend ACO algorithms to deal with multimodal optimization. First, combined with current niching methods, an adaptive multimodal continuous ACO algorithm is introduced. In this algorithm, an adaptive parameter adjustment is developed, which takes the difference among niches into consideration. Second, to accelerate convergence, a differential evolution mutation operator is alternatively utilized to build base vectors for ants to construct new solutions. Then, to enhance the exploitation, a local search scheme based on Gaussian distribution is self-adaptively performed around the seeds of niches. Together, the proposed algorithm affords a good balance between exploration and exploitation. Extensive experiments on 20 widely used benchmark multimodal functions are conducted to investigate the influence of each algorithmic component and results are compared with several state-of-the-art multimodal algorithms and winners of competitions on multimodal optimization. These comparisons demonstrate the competitive efficiency and effectiveness of the proposed algorithm, especially in dealing with complex problems with high numbers of local optima.

In this paper, a hybrid algorithm is proposed for travelling salesman problem (TSP). TSP, one of the vehicle route planning problems, is to minimize the cost of travel of a salesman in visiting all the cities in a given set, and return to the starting city. Basically, the proposed algorithm combines ant colony optimization (ACO) with genetic algorithm (GA) and can explore and exploit search spaces. It has both the advantage of ACO, the ability to find feasible solutions and to avoid premature convergence, and that of GA, the ability to avoid being trapped in local optima. The test results show that proposed algorithm finds optimum solutions effectively.

In the competitive shoe manufacturing industry, efficient production scheduling often struggles to balance minimizing makespan (MS) and reducing the number of cells, leading to increased complexity. This study introduces a biobjective optimization model to minimize the MS and the number of cells in a cellular manufacturing (CM) system. The model includes three phases: (1) a capacity phase calculates the required number of cells to meet the production demand within a suitable production rate; (2) a scheduling phase calculates the start and finish times for each product within a machine; (3) an optimization phase uses genetic algorithm (GA) for generating a set of optimal solutions considering the workforce distribution and product sequencing. The performance of the developed model was evaluated using a case study discussed in the literature to demonstrate its capabilities and highlight its superiority over similar models. These results showed a significant reduction of 0.4% in MS while maintaining the same number of cells compared to other models. A sensitivity analysis is conducted by varying the crossover and mutation probabilities. The findings indicate that the model achieves the most stable and consistent performance for paired crossover–mutation settings with crossover probabilities between 70% and 90% (corresponding to mutation probabilities between 30% and 10%), resulting in the lowest average MS and the most balanced cell utilization. The capabilities of the developed model provide production managers with reliable insights for identifying the production requirements of the shoe manufacturing company. The algorithm was also benchmarked on 12 published instances using 30 independent runs per instance to assess solution quality and stability.

In this paper, cell loading and shipment method optimisation problem in a cellular manufacturing system are studied. A hierarchical methodology that consists of mathematical optimisation model, genetic algorithms (GAs) and artificial neural networks (ANNs) were proposed. The mathematical model is compared with the GA in terms of the optimisation performance. Next, ANN model was developed as decision support tool to study the impact of GA parameters on the solution quality. Several problem sizes were experimented with the proposed GA and the mathematical model, and compared. GA was run to make a total of 648 sample solutions for the 20-job problem. Next, ANN model was built based on the sample solutions' data and the optimal ANN model is identified out of 1,000 networks. The results were also coupled with sensitivity and statistical analyses, which indicated that type of crossover and mutation operators, had the greatest impact on the solution quality.

To improve the performance and reliability of gas turbine like an aeroengine, the multi-object multi-discipline (MOMD) reliability optimization design of high press turbine (HPT) blade-tip radial running clearance (BTRRC) was first accomplished based on the mechanical dynamic assembly reliability (MDAR) theory and distributed collaborative response surface method (DCRSM). Four optimization models of MDAR were developed based on the features of assembly machinery and the thought of DCRSM, which are, respectively, called as the direct reliability optimization model (denoted by M1), the multilayer reliability optimization models (denoted by M2), the direct reliability optimization model-based probabilistic analysis (denoted by M3), and the multilayer reliability optimization model-based probabilistic analysis (denoted by M4). Through the MDAR optimization design of BTRRC by the four standard optimization models, some conclusions are drawn as follows: (1) the DCRSM is proved to be effective and feasible for MOMD MDAR optimization design with high computational efficiency and precision; (2) all the reliability optimization results of BTRRC and assembly objects satisfy the requirements of optimization design, and the optimized BTTRC variations are reduced by about 10% and obey the normal distribution, which are quite promising in improving the design and control of HPT BTRRC; (3) in computational efficiency, the computing time of M1 and M3 is far less than those of M2 and M4, meanwhile M3 and M4 are superior to M1 and M2; (4) in computational accuracy, M1 and M2 are better than M3 and M4, as well as M2 and M4 are higher than M1 and M3 theoretically. The presented study does not only fulfill the HPT BTRRC dynamic assembly design from a probabilistic optimization perspective and improve the performance and reliability of gas turbine engine, but also provides a promising approach and four valuable optimization models for MDAR optimization design. Besides, the present efforts are of great significance in enriching the theory and method of mechanical reliability design.

The current research seeks to present a proposed model for the design of a dynamic cellular manufacturing system in the Light Industries Company/Ashtar in Baghdad, one of the Iraqi industrial companies. With the aim of generating an industrial environment capable of accommodating rapid changes in the market to meet the changing and diverse needs and desires of the customer at the lowest possible cost, at the right time and the required quality. To achieve the current research relied on the methods of artificial intelligence, employing them and benefiting from them in the industrial field, especially the genetic algorithm. Accordingly, the current research included a theoretical framework for the dynamic cellular manufacturing system and the genetic algorithm, in light of what was mentioned in the Arab and foreign sources related to them. The research also adopted a field framework to design this system in the researched company using the genetic algorithm, and the researchers chose the freezers and models labs as a field for study, and in light of the results of the programming language program (MATLAB). It was reached to build a proposed model that reflects the virtual reality of this system. On the basis of that, the research reached a set of conclusions, the most important of which is the genetic algorithm that contributed significantly and effectively to finding the optimal cellular path for the dynamic cellular manufacturing system and reducing both the total time and the total cost of production. In light of this a set of proposals were presented showing the importance of shifting from the existing cellular manufacturing system in the field of study to the dynamic cellular manufacturing system.

Importance measure can be used to identify the most vulnerable components with respect to system functionality or failure. Traditional importance measures may not be effective to evaluate the contribution of an individual component if its reliability value does not fall in the full range between 0 and 1. Based on the cost-reliability relation, this paper proposes a generalized Birnbaum importance measure (GBIM) to quantify the contribution of individual components to system reliability improvement by considering reliability range, manufacturing complexity, and technology feasibility. Since GBIM possesses several unique features in terms of guiding system reliability optimization, in this paper, we further develop a GBIM-based genetic algorithm to solve a type of optimal reliability allocation problem. The numerical studies show that both the computational efficiency and the near global optimality based on GBIM outperforms the methods using the traditional importance measures.

Design of layouts for Cellular Manufacturing Systems (CMSs) has not received attention by researchers as much as cell formation in cellular manufacturing. In this paper a mathematical model, formulated as a multicriteria Quadratic Assignment Problem (QAP) is proposed for the design of layouts for CMSs with the objective of minimising the material handling cost (quantitative) and maximising the closeness rating (qualitative). A Genetic Algorithm (GA)-based tool called FUGEN, which makes use of crossover, mutation (inversion) and direct entry (elitism) with embedded fuzzy logic and Analytic Hierarchy Process (AHP) models, is developed for the design of layouts for CMSs. An attempt is made to make the model practical by considering the production volume, transfer batch size and operational sequence of parts. The proposed tool is validated using an example from the literature.

This paper presents a new strategy addressed as “service level-based smooth production strategy” for the cell formation decisions of a robust cellular manufacturing system (CMS) to handle varying demands. In this strategy, a service level concept is adapted to fix smooth production level estimated to meet the desired demand satisfaction rate (DSR) or fill rate of the customers. Besides, the model considers cross-flow and scheduling aspects, which are not often addressed in CMS designs. A non-linear integer program is formulated to evolve CMS decisions for the specified DSR under fluctuating demands. Two solution methodologies of mathematical programming using ILOG CPLEX solver and genetic algorithm (GA) with adaptive mutation and crossover operators addressed in as adaptive genetic algorithm (AGA) are proposed. The model analysis carried out under various DSR reveals that the cell formation decisions are highly sensitive to DSR. This paper also discusses how this model can be used to compare robust and reconfigurable approaches to decide the suitable approach to handle fluctuating demands with minimum cost. The performance study of solution methodologies reveals that CPLEX and AGA are efficient in finding optimal solutions to smaller-size problems. However, AGA is comparatively efficient for larger-size problems with a reasonable computational time.

Cell formation and machine layout in cellular manufacturing systems (CMs) design are considered as a crucial, yet hard and complex decision process. Owing to the nondeterministic polynomial time (NP) and combinatorial class of this problem, this paper presents an innovative heuristic approach to re‐arrange machines enabling the minimisation of inter/intra‐ cellular movements as well as the cost of material handling between machines, therefore increasing group efficiency and efficacy. The heuristic approach, which is based on group technology, genetic algorithms, and desirability function, determines the optimal solution for flexible cell formation and machine layout within each cell. Flexibility refers to an explicit improvement using the desirability function to modify cell design by altering the ratio data; that is, the weight factor to meet demand flexibility. Specifically, the desirable function proposed here to provide the optimal setting of the weighting factor as a key factor which enables CMs design the flexibility to control the cell size. Promised results were obtained when the proposed approach was applied to a case study. Practical implications and recommendations are provided for use by decision makers in the design of CMs.