Showing papers in "Journal of Intelligent Manufacturing in 2012"
TL;DR: The ABC algorithm is applied to engineering design problems by extending the basic ABC algorithm simply by adding a constraint handling technique into the selection step of the ABC algorithm in order to prefer the feasible regions of entire search space.
Abstract: Engineering design problems are generally large scale or nonlinear or constrained optimization problems. The Artificial Bee Colony (ABC) algorithm is a successful tool for optimizing unconstrained problems. In this work, the ABC algorithm is used to solve large scale optimization problems, and it is applied to engineering design problems by extending the basic ABC algorithm simply by adding a constraint handling technique into the selection step of the ABC algorithm in order to prefer the feasible regions of entire search space. Nine well-known large scale unconstrained test problems and five well-known constrained engineering problems are solved by using the ABC algorithm and the performance of ABC algorithm is compared against those of state-of-the-art algorithms.
468 citations
TL;DR: An artificial neural network (ANN) based method is developed for achieving more accurate remaining useful life prediction of equipment subject to condition monitoring and is validated using real-world vibration monitoring data collected from pump bearings in the field.
Abstract: Accurate equipment remaining useful life prediction is critical to effective condition based maintenance for improving reliability and reducing overall maintenance cost. In this paper, an artificial neural network (ANN) based method is developed for achieving more accurate remaining useful life prediction of equipment subject to condition monitoring. The ANN model takes the age and multiple condition monitoring measurement values at the present and previous inspection points as the inputs, and the life percentage as the output. A function generalized from the Weibull failure rate function is used to fit each condition monitoring measurement series for a failure history, and the fitted measurement values are used to form the ANN training set so as to reduce the effects of the noise factors that are irrelevant to the equipment degradation. A validation mechanism is introduced in the ANN training process to improve the prediction performance of the ANN model. The proposed ANN method is validated using real-world vibration monitoring data collected from pump bearings in the field. A comparative study is performed between the proposed ANN method and an adapted version of a reported method, and the results demonstrate the advantage of the proposed method in achieving more accurate remaining useful life prediction.
314 citations
TL;DR: Three different type of support vector machines (SVMs) tools such as least square SVM, Spider SVM and SVM-KM and an artificial neural network model and an feedforward neural network were developed to estimate the surface roughness values of AISI 304 austenitic stainless steel in CNC turning operation.
Abstract: In the present investigation, three different type of support vector machines (SVMs) tools such as least square SVM (LS-SVM), Spider SVM and SVM-KM and an artificial neural network (ANN) model were developed to estimate the surface roughness values of AISI 304 austenitic stainless steel in CNC turning operation. In the development of predictive models, turning parameters of cutting speed, feed rate and depth of cut were considered as model variables. For this purpose, a three-level full factorial design of experiments (DOE) method was used to collect surface roughness values. A feedforward neural network based on backpropagation algorithm was a multilayered architecture made up of 15 hidden neurons placed between input and output layers. The prediction results showed that the all used SVMs results were better than ANN with high correlations between the prediction and experimentally measured values.
160 citations
TL;DR: It is concluded that the proposed model has the capability of dealing with a wide range of desired criteria and to select any type of machine tool required for building an FMC.
Abstract: The selection process of a suitable machine tool among the increased number of alternatives has been an important issue for manufacturing companies for years. This is because the improper selection of a machine tool may cause many problems that will affect the overall performance. In this paper, a decision support system (DSS) is presented to select the best alternative machine using a hybrid approach of fuzzy analytic hierarchy process (fuzzy AHP) and preference ranking organization method for enrichment evaluation (PROMETHEE). A MATLAB- based fuzzy AHP is used to determine the weights of the criteria and it is called program for Priority Weights of the Evaluation Criteria (PWEC), and the PROMETHEE method is applied for the final ranking. The proposed model is structured to select the most suitable computer numerical controlled (CNC) turning centre machine for a flexible manufacturing cell (FMC) among the alternatives which are assigned from a database (DB) created for this purpose. A numerical example is presented to show the applicability of the model. It is concluded that the proposed model has the capability of dealing with a wide range of desired criteria and to select any type of machine tool required for building an FMC.
119 citations
TL;DR: This paper presents a framework to show how other strategies such as Quick Response manufacturing/POLCA, Theory of Constraints, Flexible/Reconfigurable Manufacturing Systems, etc. can be integrated with lean in MC environments.
Abstract: Mass customization (MC) manufacturing requires high flexibility to respond to customer needs in a timely manner. Lean manufacturing principles can be easily applied to situations with low levels of MC. However, as the degree of customization increases and customer involvement occurs earlier in the design and fabrication stages, the direct application of lean principles to maintain flow and low levels of inventory becomes difficult. This paper presents a framework to show how other strategies such as Quick Response manufacturing/POLCA, Theory of Constraints, Flexible/Reconfigurable Manufacturing Systems, etc. can be integrated with lean in MC environments. A case study of boat mass customizer is then used to demonstrate how their operations are transformed by for more efficient MC. Simulation models are used to compare pre- and post-improvement performance.
117 citations
TL;DR: A new approach to generate the dynamic process plan for reconfigurable manufacturing system using an adapted NSGA-2 algorithm with the aim of reducing the manufacturing cost and time is proposed.
Abstract: With burgeoning global markets and increasing customer demand, it is imperative for companies to respond quickly and cost effectively to be present and to take the lead among the competitors. Overall, this requires a changeable structure of the organization to cater to a wide product variety. It can be attained through adoption of the concept of reconfigurable manufacturing system (RMS) that comprises of reconfigurable machines, controllers and software support systems. In this paper, we propose a new approach to generate the dynamic process plan for reconfigurable manufacturing system. Initially, the requirements of the parts/products are assessed which are then compared with the functionality offered by machines comprising manufacturing system. If the production is feasible an optimal process plan is generated, otherwise the system shows an error message showing lack of functionality. Using an adapted NSGA-2 algorithm, a multi-objective scenario is considered with the aim of reducing the manufacturing cost and time. With the help of a numerical example, the efficacy of the proposed approach is demonstrated.
114 citations
TL;DR: Experimental results demonstrate that the CCM algorithm outperforms both LEACH and PEGASIS in terms of the product of consumed energy and delay, weighting the overall performance of both energy consumption and transmission delay.
Abstract: Wireless sensor networks (WSNs) are an emerging technology for monitoring physical world. Different from the traditional wireless networks and ad hoc networks, the energy constraint of WSNs makes energy saving become the most important goal of various routing algorithms. For this purpose, a cluster based routing algorithm LEACH (low energy adaptive clustering hierarchy) has been proposed to organize a sensor network into a set of clusters so that the energy consumption can be evenly distributed among all the sensor nodes. Periodical cluster head voting in LEACH, however, consumes non-negligible energy and other resources. While another chain-based algorithm PEGASIS (power- efficient gathering in sensor information systems) can reduce such energy consumption, it causes a longer delay for data transmission. In this paper, we propose a routing algorithm called CCM (Chain-Cluster based Mixed routing), which makes full use of the advantages of LEACH and PEGASIS, and provide improved performance. It divides a WSN into a few chains and runs in two stages. In the first stage, sensor nodes in each chain transmit data to their own chain head node in parallel, using an improved chain routing protocol. In the second stage, all chain head nodes group as a cluster in a self- organized manner, where they transmit fused data to a voted cluster head using the cluster based routing. Experimental results demonstrate that our CCM algorithm outperforms both LEACH and PEGASIS in terms of the product of consumed energy and delay, weighting the overall performance of both energy consumption and transmission delay.
100 citations
TL;DR: This paper contributes to the re-vitalization of RFID efforts in manufacturing industries by presenting a real-life case study of applying RFID for managing material distribution in a complex assembly shop-floor at a large air conditioner manufacturer.
Abstract: Radio Frequency Identification (RFID) technologies provide automatic and accurate object data capturing capability and enable real-time object visibility and traceability. Potential benefits have been widely reported for improving manufacturing shop-floor management. However, reports on how such potentials come true in real-life shop-floor daily operations are very limited. As a result, skeptics overwhelm enthusiasm. This paper contributes to the re-vitalization of RFID efforts in manufacturing industries by presenting a real-life case study of applying RFID for managing material distribution in a complex assembly shop-floor at a large air conditioner manufacturer. The case study discusses how technical, social and organizational issues have been addressed throughout the project within the company. It is hoped that insights and lessons gained be generalized for future efforts across household electrical appliance manufacturers that share similar shop-floor.
98 citations
TL;DR: Two model-based approaches for tool wear monitoring on the basis of neuro-fuzzy techniques are presented and it is demonstrated that the transductive neuro- fuzzy model provides better error-based performance indices for detecting tool wear than the inductives and than the evolving neuro-Fuzzy models.
Abstract: Tool wear detection is a key issue for tool condition monitoring. The maximization of useful tool life is frequently related with the optimization of machining processes. This paper presents two model-based approaches for tool wear monitoring on the basis of neuro-fuzzy techniques. The use of a neuro-fuzzy hybridization to design a tool wear monitoring system is aiming at exploiting the synergy of neural networks and fuzzy logic, by combining human reasoning with learning and connectionist structure. The turning process that is a well-known machining process is selected for this case study. A four-input (i.e., time, cutting forces, vibrations and acoustic emissions signals) single-output (tool wear rate) model is designed and implemented on the basis of three neuro-fuzzy approaches (inductive, transductive and evolving neuro-fuzzy systems). The tool wear model is then used for monitoring the turning process. The comparative study demonstrates that the transductive neuro-fuzzy model provides better error-based performance indices for detecting tool wear than the inductive neuro-fuzzy model and than the evolving neuro-fuzzy model.
90 citations
TL;DR: The three changeability indices are proven to be effective for the change impact assessment through a real-world case of Roots Blowers and can help the designers avoid changing to “expensive” parts or subsystems.
Abstract: The complex product design is a continuously changing process from customer requirements to a maturity design. During this process a change of one part will, in most cases, causes changes in other parts and even the whole product. The assessment for the impacts of such changes can support designers' designing and help manager to manage redesigning. A complex product can be considered as a weighted network of parts, subassemblies, or subsystems. Based on the theory of weighted networks, three changeability indices (degree-changeability, reach-changeability and between-changeability) are presented. Degree-changeability is used to calculate the direct change impacts. Reach-changeability is used to assess the indirectly change impacts because of propagation. If a part influences the other parts dramatically and it is also influenced by them, this part can be predicted by between-changeability. Finally, the three changeability indices are proven to be effective for the change impact assessment through a real-world case of Roots Blowers. With the analysis, the designers can avoid changing to "expensive" parts or subsystems.
87 citations
TL;DR: A fuzzy analytic network process model to evaluate various aspects of suppliers is proposed and a case study of IC packaging company selection in Taiwan is presented, and the proposed model is applied to facilitate the decision process.
Abstract: Supplier selection has been a popular topic since the selection of the most appropriate supplier for cooperation is being increasingly important for the success of an enterprise. The problem is multi-criteria in nature, and a variety of multi-criteria decision making methodologies have been proposed. However, most of them did not take into account the interrelationships among the critical success factors and the fuzziness of the data involved in deciding the preferences of the factors. The objective of this research is to propose a fuzzy analytic network process model to evaluate various aspects of suppliers. With the consultation with the experts, the proposed model can consider the feedback and interdependency of factors in a network, and the factors are pairwise compared under an uncertain environment. The weights of factors can be calculated, and the final priority of suppliers obtained. Semiconductor industry becomes increasingly globalize competitive nowadays, and a good supply chain relationship is essential for a company to survive and to acquire reasonable profit. Thus, a case study of IC packaging company selection in Taiwan is presented, and the proposed model is applied to facilitate the decision process. The priorities of the factors and the ranking of the suppliers can be a recommendation or reference for decision makers when making a supplier evaluation and selection decision.
TL;DR: The hybrid model proposed here surpasses most similar systems in solving many more traditional benchmark problems and real-life problems and achieves by the combined impact of several small but important features such as powerful chromosome representation, effective genetic operators, restricted neighbourhood strategies and efficient search strategies along with innovative initial solutions.
Abstract: In recent decades many attempts have been made at the solution of Job Shop Scheduling Problem using a varied range of tools and techniques such as Branch and Bound at one end of the spectrum and Heuristics at the other end However, the literature reviews suggest that none of these techniques are sufficient on their own to solve this stubborn NP-hard problem Hence, it is postulated that a suitable solution method will have to exploit the key features of several strategies We present here one such solution method incorporating Genetic Algorithm and Tabu Search The rationale behind using such a hybrid method as in the case of other systems which use GA and TS is to combine the diversified global search and intensified local search capabilities of GA and TS respectively The hybrid model proposed here surpasses most similar systems in solving many more traditional benchmark problems and real-life problems This, the system achieves by the combined impact of several small but important features such as powerful chromosome representation, effective genetic operators, restricted neighbourhood strategies and efficient search strategies along with innovative initial solutions These features combined with the hybrid strategy employed enabled the system to solve several benchmark problems optimally, which has been discussed elsewhere in Meeran and Morshed (8th Asia Pacific industrial engineering and management science conference, Kaohsiung, Taiwan, 2007) In this paper we bring out the system's practical usage aspect and demonstrate that the system is equally capable of solving real life Job Shop problems
TL;DR: The Gauss-Newton regression method and back-propagation neural network are used as basic model to forecast the cycle time of the production line, where WIP, capacity, utilization, average layers, and throughput are rendered as input factors for indentifying effective rules to control the levels of the corresponding factors as well as reduce the cycleTime.
Abstract: Semiconductor manufacturing is one of the most complicated production processes with the challenges of dynamic job arrival, job re-circulation, shifting bottlenecks, and lengthy fabrication process. Owing to the lengthy wafer fabrication process, work in process (WIP) usually affects the cycle time and throughput in the semiconductor fabrication. As the applications of semiconductor have reached the era of consumer electronics, time to market has played an increasingly critical role in maintaining a competitive advantage for a semiconductor company. Many past studies have explored how to reduce the time of scheduling and dispatching in the production cycle. Focusing on real settings, this study aims to develop a manufacturing intelligence approach by integrating Gauss-Newton regression method and back-propagation neural network as basic model to forecast the cycle time of the production line, where WIP, capacity, utilization, average layers, and throughput are rendered as input factors for indentifying effective rules to control the levels of the corresponding factors as well as reduce the cycle time. Additionally, it develops an adaptive model for rapid response to change of production line status. To evaluate the validity of this approach, we conducted an empirical study on the demand change and production dynamics in a semiconductor foundry in Hsinchu Science Park. The approach proved to be successful in improving forecast accuracy and realigning the desired levels of throughput in production lines to reduce the cycle time.
TL;DR: Experimental results show that the bearing fault features extracted using both traditional vibration analysis methods and the proposed method give clear bearing heath degradation trend for the dataset collected under normal operating conditions, however, for the data collected under abnormal operating conditions it fails to show the bearing health degradation trend.
Abstract: Over the past years, investigation on condition-based maintenance (CBM) technique on bearing has been conducted. Bearing diagnostics and prognostics are the important aspects in CBM. A key to the success of using vibration data for bearing fault diagnostics and bearing lifecycle prognostics is a quantified relationship between bearing damage and bearing fault features. To establish such a quantitative relationship, effective signal processing techniques to extract bearing fault features from vibration signals are needed. This paper describes a newly developed fault feature extraction method for bearing prognostics. The effectiveness of the method is demonstrated with two real bearing run-to-failure test datasets: one collected under normal operating conditions and another one under abnormal operating conditions. Experimental results show that the bearing fault features extracted using both traditional vibration analysis methods and the proposed method give clear bearing heath degradation trend for the dataset collected under normal operating conditions. However, for the data collected under abnormal operating conditions, bearing fault features obtained using traditional vibration analysis methods fail to show the bearing health degradation trend while the fault features extracted using the proposed method give consistent bearing degradation trends.
TL;DR: This paper introduces DMM through its major components including a multi-agent framework, a formal ontology for representation of manufacturing services as well as a matchmaking methodology used for connecting buyers and sellers of manufacturing Services based on their semantic similarities.
Abstract: Manufacturing Market is a market in which manufacturing process capacity is the object of trade. In a market, units of capacity, represented as manufacturing services, can be acquired as needed and when needed, thus making supply chains more responsive to fluctuations in supply and demand. Although Manufacturing Market can be built physically as a spot market, its benefits can be better realized in a web-based framework. We refer to the web-based version of Manufacturing Market as Digital Manufacturing Market (DMM). The major challenges in deployment of a virtual market for manufacturing services include standard representation of manufacturing needs and capabilities, incorporation of intelligent supplier search and evaluation mechanism, and automation of supply chain configuration process. This paper introduces DMM through its major components including a multi-agent framework, a formal ontology for representation of manufacturing services as well as a matchmaking methodology used for connecting buyers and sellers of manufacturing services based on their semantic similarities. The ultimate goal of the proposed framework is to enable autonomous deployment of manufacturing supply chains based on the specific technological requirements defined by particular work orders.
TL;DR: An attempt has been made to estimate the weld bead width and depth of penetration from the infra red thermal image of the weld pool using artificial neural network models during A-TIG welding of 3 mm thick type 316 LN stainless steel plates.
Abstract: It is necessary to estimate the weld bead width and depth of penetration using suitable sensors during welding to monitor weld quality. Among the vision sensors, infra red sensing is the natural choice for monitoring welding processes as welding is inherently a thermal processing method. An attempt has been made to estimate the weld bead width and depth of penetration from the infra red thermal image of the weld pool using artificial neural network models during A-TIG welding of 3 mm thick type 316 LN stainless steel plates. Real time infra red images were captured using IR camera for the entire weld length during A-TIG welding at various current values. The image features such as length and width of the hot spot, peak temperature, and other features using line scan analysis are extracted using image processing techniques corresponding to particular locations of the weld joint. These parameters along with their respective current values are used as inputs while the measured weld bead width and depth of penetration are used as output of the neural network models. Accurate ANN models predicting weld bead width (9-11-1) and depth of penetration (9-9-1) have been developed. The correlation coefficient values obtained were 0.98862 and 0.99184 between the measured and predicted values of weld bead width and depth of penetration respectively.
TL;DR: This work develops a physical programming based approach to deal with the multi-objective condition based maintenance optimization problem and shows how the decision maker can systematically and efficiently make good tradeoff between the cost objective and reliability objective.
Abstract: In condition based maintenance (CBM) optimization, the main optimization objectives include maximizing reliability and minimizing maintenance costs, which are often times conflicting to each other. In this work, we develop a physical programming based approach to deal with the multi-objective condition based maintenance optimization problem. Physical programming presents two major advantages: (1) it is an efficient approach to capture the decision makers' preferences on the objectives by eliminating the iterative process of adjusting the weights of the objectives, and (2) it is easy to use in that decision makers just need to specify physically meaningful boundaries for the objectives. The maintenance cost and reliability objectives are calculated based on proportional hazards model and a control limit CBM replacement policy. With the proposed approach, the decision maker can systematically and efficiently make good tradeoff between the cost objective and reliability objective. An example is used to illustrate the proposed approach.
TL;DR: A new multi-objective genetic algorithm is applied to solve the simple assembly line balancing problem of type 2 (SALBP-2) with fuzzy job processing times since uncertainty, variability, and imprecision are often occurred in real-world production systems.
Abstract: This paper presents a fuzzy extension of the simple assembly line balancing problem of type 2 (SALBP-2) with fuzzy job processing times since uncertainty, variability, and imprecision are often occurred in real-world production systems. The jobs processing times are formulated by triangular fuzzy membership functions. The total fuzzy cost function is formulated as the weighted-sum of two bi-criteria fuzzy objectives: (a) Minimizing the fuzzy cycle time and the fuzzy smoothness index of the workload of the line. (b) Minimizing the fuzzy cycle time of the line and the fuzzy balance delay time of the workstations. A new multi-objective genetic algorithm is applied to solve the problem whose performance is studied and discussed over known test problems taken from the open literature.
TL;DR: An off-line planning method for the control parameters of the grinding robot based on an adaptive modeling method is proposed in this paper and the results of the blade grinding experiments demonstrate that this approach can control the material removal ofThe grinding system effectively.
Abstract: As a kind of manufacturing system with a flexible grinder, the material removal of a robot belt grinding system is related to a variety of factors, such as workpiece shape, contact force, robot velocity, and belt wear. Some factors of the grinding process are time-variant. Therefore, it is a challenge to control grinding removal precisely for free-formed surfaces. To develop a high-quality robot grinding system, an off-line planning method for the control parameters of the grinding robot based on an adaptive modeling method is proposed in this paper. First, we built an adaptive model based on statistic machine learning. By transferring the old samples into the new samples space formed by the in-situ measurement data, the adaptive model can track the dynamic working conditions more rapidly. Based on the adaptive model the robot control parameters are calculated using the cooperative particle swarm optimization in this paper. The optimization method aims to smoothen the trajectories of the control parameters of the robot and shorten the response time in the transition process. The results of the blade grinding experiments demonstrate that this approach can control the material removal of the grinding system effectively.
TL;DR: A novel framework and approach to design cluster supply chain without across-chain horizontal cooperation is provided and a hybrid method to find solution is presented, and a computational study is presented to investigate values of decision variables and their influence on Cluster supply chain design.
Abstract: Intelligent model design of complex system becomes a key issue for organization responsiveness to uncertainties. In the real business world, the rule of competition between one firm verse another is replaced by a chain verse another chain, the cooperation is the same, where does it occur? At industrial cluster, there are a multiple of rivals or potential competitors for each member of value chain, industrial cluster location not only contains a couple of focal firms locating at the same tier, but includes the corresponding upstream and downstream firms as well, all of which concentrate on a close geographical site. For adopting to ever-changing market and sever competition, it is most likely to form multiple paralleled single supply chains for each focal firm of industrial cluster, these paralleled single supply chains compete and cooperate with each other. Recent researches regarding supply chain design mainly focus on a limited tier in single supply chain, which only take into account vertical cooperation and ignore the across-chain horizontal one. This paper, based on cluster supply chain, provides a novel framework and approach to design cluster supply chain without across-chain horizontal cooperation, then by introducing item allocation proportion of vertical and horizontal cooperation (α: 1−α), the cluster supply chain design with across-chain horizontal cooperation is developed, then presents a hybrid method to find solution, at last, computational study is presented to investigate values of decision variables and their influence on cluster supply chain design.
TL;DR: The results suggest that the root mean square (RMS) indicator is a better statistical indicator than the Kurtosis indicator to reflect the crack propagation in the early stage of gearbox vibration monitoring approaches.
Abstract: Model-based gear dynamic analysis and simulation has been a promising way for developing effective gearbox vibration monitoring approaches. In this paper, based on the dynamic model of a one-stage gearbox with spur gears and one tooth crack, statistical indicators and the discrete wavelet transform (DWT) technique are investigated to identify effective and sensitive health indicators for reflecting the crack propagation level. The results suggest that the root mean square (RMS) indicator is a better statistical indicator than the Kurtosis indicator to reflect the crack propagation in the early stage; the RMS indicator based on the residual signal segments that are strongly affected by the crack is more sensitive; the proposed DWT approach can improve the sensitivity of the RMS indicator, and the RMS indicator becomes more sensitive with the increase of the DWT level up to a best DWT level, beyond which either the monotonicity is lost or the sensitivity decreases; the proposed approach is effective with the presence of noise; with the increase of the noise level, the DWT level at which the best performance is achieved, and thus the sensitivity, decreases. Gearbox systems with different sizes and different input shaft frequencies are also investigated, and it is found that the observations presented above hold for different gearbox system settings.
TL;DR: In this article, a restricted simulated annealing (RSA) algorithm which incorporates a restricted search strategy is presented to minimize the makespan of the search effort required to find the best neighborhood solution by eliminating ineffective job moves.
Abstract: This study considers the problem of scheduling jobs on unrelated parallel machines with machine-dependent and job sequence-dependent setup times. In this study, a restricted simulated annealing (RSA) algorithm which incorporates a restricted search strategy is presented to minimize the makespan. The proposed RSA algorithm can effective reduce the search effort required to find the best neighborhood solution by eliminating ineffective job moves. The effectiveness and efficiency of the proposed RSA algorithm is compared with the basic simulated annealing and existing meta-heuristics on a benchmark problem dataset used in earlier studies. Computational results indicate that the proposed RSA algorithm compares well with the state-of-the-art meta-heuristic for small-sized problems, and significantly outperforms basic simulated annealing algorithm and existing algorithms for large-sized problems.
TL;DR: This paper formulate this problem using queuing theory and solve the model by a genetic algorithm within the desirability function framework by minimizing the average customer waiting time and minimize the average facility idle-time percentage.
Abstract: In many service and industrial applications of the facility location problem, the number of required facilities along with allocation of the customers to the facilities are the two major questions that need to be answered. In this paper, a facility location problem with stochastic customer demand and immobile servers is studied. Two objectives considered in this problem are: (1) minimizing the average customer waiting time and (2) minimizing the average facility idle-time percentage. We formulate this problem using queuing theory and solve the model by a genetic algorithm within the desirability function framework. Several examples are presented to demonstrate the applications of the proposed methodology.
TL;DR: An integrated model for experimental design of processes with multiple correlated responses is proposed, composed of three stages which use Taguchi’s quality loss function to present relative significance of responses and multivariate statistical methods to uncorrelate and synthesise responses into a single performance measure.
Abstract: The Taguchi robust parameter design has been widely used over the past decade to solve many single-response process parameter designs. However, the Taguchi method is unable to deal with multi-response problems that are of main interest today, owing to increasing complexity of manufacturing processes and products. Several recent studies have been conducted in order to solve this problem. But, they did not effectively treat situations where responses are correlated and situations in which control factors have continuous values. This study proposed an integrated model for experimental design of processes with multiple correlated responses, composed of three stages which (1) use expert system, designed for selecting an inner and an outer orthogonal array, to design an actual experiment, (2) use Taguchi's quality loss function to present relative significance of responses, and multivariate statistical methods to uncorrelate and synthesise responses into a single performance measure, (3) use neural networks to construct the response function model and genetic algorithms to optimise parameter design. The effectiveness of the proposed model is illustrated with three examples. Results of analysis showed that the proposed approach could yield a better solution in terms of the optimal parameters setting that results in a higher process performance measure than the traditional experimental design.
TL;DR: A novel pattern-based genetic algorithm is proposed that is designed to handle routing and partitioning concurrently for sensor-based multi-robot coverage path planning problem.
Abstract: Sensor-based multi-robot coverage path planning problem is one of the challenging problems in managing flexible, computer-integrated, intelligent manufacturing systems. A novel pattern-based genetic algorithm is proposed for this problem. The area subject to coverage is modeled with disks representing the range of sensing devices. Then the problem is defined as finding a sequence of the disks for each robot to minimize the coverage completion time determined by the maximum time traveled by a robot in a mobile robot group. So the environment needs to be partitioned among robots considering their travel times. Robot turns cause the robot to slow down, turn and accelerate inevitably. Therefore, the actual travel time of a mobile robot is calculated based on the traveled distance and the number of turns. The algorithm is designed to handle routing and partitioning concurrently. Experiments are conducted using P3-DX mobile robots in the laboratory and simulation environment to validate the results.
TL;DR: A new approach for the organization of the ‘control’ function in a Job Shop having the characteristics of working with small series relies on the use of the holonic paradigm on an isoarchic architecture and on a decision-making capacity based on a multicriteria analysis.
Abstract: Faced with international competition, industrial production increasingly requires implementation conditions which, in some cases, lead to seek new techniques for workshop control. This is the case when it is asked to establish Just in Time management in a Job Shop having the characteristics of working with small series. A new approach for the organization of the `control' function in such a context is presented here. This approach relies on the use of the holonic paradigm on an isoarchic architecture and on a decision-making capacity based on a multicriteria analysis. The various concepts of this approach are addressed first. Then, the multicriteria decision mechanisms that are used are detailed, as well as the implementation and instrumentation phases. The first results that were obtained are presented.
TL;DR: A kanban controlled and heijunka leveled production system where the arriving demands are controlled and limited by a kanban loop and the aim is to determine the optimal number of production kanbans, and thus the buffer size that guarantees a given service level.
Abstract: Heijunka is a key-element of the Toyota production system which levels the release of production kanbans in order to achieve an even production flow over all possible types of products, thus, e.g. reducing the bullwhip effect. In this paper we analyze a kanban controlled and heijunka leveled production system where the arriving demands are controlled and limited by a kanban loop. The production system is modeled as a queueing network with synchronization stations. The aim is to determine the optimal number of production kanbans, and thus the buffer size that guarantees a given service level.
TL;DR: An integrated approach using the Taguchi method, grey relational analysis and a neural network to optimize the weld bead geometry in a novel gas metal arc (GMA) welding process is presented.
Abstract: The objective of this paper is to present an integrated approach using the Taguchi method (TM), grey relational analysis (GRA) and a neural network (NN) to optimize the weld bead geometry in a novel gas metal arc (GMA) welding process. The TM is first used to construct a database for the NN. The GRA is adopted to solve the problem of multiple performance characteristics in a GMA welding process using activating flux. The grey relational grade obtained from the GRA is used as the output of the back-propagation (BP) NN. Then, a NN with the Levenberg-Marquardt BP (LMBP) algorithm is used to provide the nonlinear relationship between welding parameters and grey relational grade of each weldment. The optimal parameters of the novel GMA welding process were determined by simulating parameters using a well-trained BPNN model. Experimental results illustrate the proposed approach.
TL;DR: This work proposes a system that consists of an optimisation module, a process control module and a knowledge based evaluation module to optimize feed-rate, and the main function of the Process Control module is process monitoring and control.
Abstract: Inappropriate machining conditions such as cutting forces cause tool failures, poor surface quality and worst of all machine breakdowns. This may be avoided by using optimal machining parameters, e.g. feed-rate, and continuing to monitor it throughout the machining process. To optimize feed-rate, we propose a system that consists of an optimisation module, a process control module and a knowledge based evaluation module. STEP-NC is the underlying data model for optimisation. Given the nominal powers, the cutting force can be estimated based on the higher-level production information such as workpiece properties, tool materials and geometries, and machine capabilities. The main function of the Process Control module is process monitoring and control. The output is the desired actual feed-rate. Finally, the actual feed-rate is recorded and evaluated in the Knowledge Based Evaluation module.
TL;DR: A RFID-enabled real- time manufacturing information tracking infrastructure (RTMITI) is proposed to address the real-time manufacturing data capturing and manufacturing information processing methods for extended enterprises.
Abstract: In extended enterprises, real-time manufacturing information tracking plays an important role and aims to provide the right information to the right person at the right time in the right format to achieve optimal production management among the involved enterprises. However, many enterprises are caused by lack of timely, accurate and consistent manufacturing data. The laggard information transfer flow and the unmatched information transfer method bring extended enterprises much more uncertainty and unknowingness. This paper proposes a RFID-enabled real-time manufacturing information tracking infrastructure (RTMITI) to address the real-time manufacturing data capturing and manufacturing information processing methods for extended enterprises. Following the proposed infrastructure, the traditional manufacturing resources such as employees, machines and materials are equipped with RFID devices (Readers and Tags) to build the real-time data capturing environment. In addition, a series of manufacturing information processing methods are established to calculate and track the real-time manufacturing information such as real-time manufacturing cost, progress, WIP (Work-in-progress) inventory etc. in parts/assemblies/products at machines/shop floors/enterprises/ extended enterprises levels. Finally, a case study is given to demonstrate the developed framework and corresponding methodologies.