Manufacturing cell formation using a new self-organizing neural network

Cellular manufacturing consists of grouping similar machines in cells and dedicating each of them to process a family of similar part types. In this paper, grouping parts into families and machines into cells is done in two steps: first, part families are formed and then machines are assigned. In phase one, weighted similarity coefficients are computed and parts are clustered using a new self-organizing neural network. In phase two, a linear network flow model is used to assign machines to families. To test the proposed approach, different problems from the literature have been solved. As benchmarks we have used a Maximum Spanning Tree heuristic.     

A hybrid genetic-variable neighborhood search algorithm for the cell formation problem based on grouping efficacy

Cell formation problem attempts to group machines and part families in dedicated manufacturing cells such that the number of voids and exceptional elements in cells are minimized. In this paper, we presented a linear fractional programming model with the objective of maximizing the grouping efficacy while the number of cells is unknown. To show the effectiveness of the proposed model, two test problems were applied. Then, to solve the model for real-sized applications, a hybrid meta-heuristic algorithm in which genetic algorithm and variable neighborhood search are combined. Using the grouping efficacy measure, we have also compared the performance of the proposed algorithm on a set of 35 test problems from the literature. The results show that the proposed GA-VNS method outperforms the state-of-the-art algorithms.     

Group technology based adaptive cell formation using predator-prey genetic algorithm

In recent years, there has been a considerable growth of application of group technology in cellular manufacturing. This has led to investigation of the primary cell formation problem (CFP), both in classical and soft-computing domain. Compared to more well-known and analytical techniques like mathematical programming which have been used rigorously to solve CFPs, heuristic approaches have yet gained the same level of acceptance. In the last decade we have seen some fruitful attempts to use evolutionary techniques like genetic algorithm (GA) and Ant Colony Optimization to find solutions of the CFP. The primary aim of this study is to investigate the applicability of a fine grain variant of the predator-prey GA (PPGA) in CFPs. The algorithm has been adapted to emphasize local selection strategy and to maintain a reasonable balance between prey and predator population, while avoiding premature convergence. The results show that the algorithm is competitive in identifying machine-part clusters from the initial CFP matrix with significantly less number of iterations. The algorithm scaled efficiently for large size problems with competitive performance. Optimal cluster identification is then followed by removal of the bottleneck elements to give a final solution with minimum inter-cluster transition cost. The results give considerable impetus to study similar NP-complete combinatorial problems using fine-grain GAs in future.     

Machine grouping using sequence-based similarity coefficients and neural networks

Most neural network approaches to the cell formation problem do not use information on the sequence of operations on part types. They only use as input the binary part-machine incidence matrix. In this paper we investigate two sequence-based neural network approaches for cell formation. The objective function considered is the minimization of transportation costs (including both intracellular and intercellular movements). Constraints on the minimum and maximum number of machines per cell can be imposed. The problem is formulated mathematically and shown to be equivalent to a quadratic programming integer program that uses symmetric, sequence-based similarity coefficients between each pair of machines. Of the two energy-based neural network approaches investigated, namely Hopfield model and Potts Mean Field Annealing, the latter seems to give better and faster solutions, although not as good as a Tabu Search algorithm used for benchmarking.     

Genetic algorithm and large neighbourhood search to solve the cell formation problem

We first introduce a local search procedure to solve the cell formation problem where each cell includes at least one machine and one part. The procedure applies sequentially an intensification strategy to improve locally a current solution and a diversification strategy destroying more extensively a current solution to recover a new one. To search more extensively the feasible domain, a hybrid method is specified where the local search procedure is used to improve each offspring solution generated with a steady state genetic algorithm. The numerical results using 35 most widely used benchmark problems indicate that the line search procedure can reduce to 1% the average gap to the best-known solutions of the problems using an average solution time of 0.64 s. The hybrid method can reach the best-known solution for 31 of the 35 benchmark problems, and improve the best-known solution of three others, but using more computational effort.     

A hybrid grouping genetic algorithm for the cell formation problem

The machine-part cell formation problem consists of constructing a set of machine cells and their corresponding product families with the objective of minimizing the inter-cell movement of the products while maximizing machine utilization. This paper presents a hybrid grouping genetic algorithm for the cell formation problem that combines a local search with a standard grouping genetic algorithm to form machine-part cells. Computational results using the grouping efficacy measure for a set of cell formation problems from the literature are presented. The hybrid grouping genetic algorithm is shown to outperform the standard grouping genetic algorithm by exceeding the solution quality on all test problems and by reducing the variability among the solutions found. The algorithm developed performs well on all test problems, exceeding or matching the solution quality of the results presented in previous literature for most problems.     

Manufacturing features recognition using backpropagation neural networks

A backpropagation neural network (BPN) is applied to the problem of feature recognition from a boundary representation (B-rep) solid model to facilitate process planning of manufactured products. It is based on the use of the face complexity code to represent the features and a neural network for the analysis of the recognition. The face complexity code is a measure of the face complexity of a feature based on the convexity or concavity of the surrounding geometry. The codes for various features are fed to the network for analysis. A backpropagation network is implemented for recognition of features and tested on published results to measure its performance. Any two or more features having significant differences in face complexity codes were used as exemplars for training the network. A new feature presented to the network is associated with one of the existing clusters, if they are similar, or the network creates a new cluster, if otherwise. Experimental results show that the network was consistent in recognizing features, hence is appropriate for application to the problem of feature recognition in automated manufacturing environment.     

Effective data mining using neural networks

Classification is one of the data mining problems receiving great attention recently in the database community. The paper presents an approach to discover symbolic classification rules using neural networks. Neural networks have not been thought suited for data mining because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or interpretation by humans. With the proposed approach, concise symbolic rules with high accuracy can be extracted from a neural network. The network is first trained to achieve the required accuracy rate. Redundant connections of the network are then removed by a network pruning algorithm. The activation values of the hidden units in the network are analyzed, and classification rules are generated using the result of this analysis. The effectiveness of the proposed approach is clearly demonstrated by the experimental results on a set of standard data mining test problems     

Intelligent data structures selection using neural networks

It is well known that abstract data types represent the core for any software application, and a proper use of them is an essential requirement for developing a robust and efficient system. Data structures are essential in obtaining efficient algorithms, having a major importance in the software development process. Selecting and creating the appropriate data structure for implementing an abstract data type can greatly impact the performance and the efficiency of the software systems. It is not a trivial problem for a software developer, as it is hard to anticipate all the use scenarios of the deployed application, and a static selection before the system’s execution is, generally, not accurate. In this paper, we are focusing on the problem of dynamic selection of efficient data structures for abstract data types implementation using a supervised learning approach. In order to dynamically select the most suitable representation for an aggregate according to the software system’s current execution context, a neural network will be used. We experimentally evaluate the proposed technique on a case study, emphasizing the advantages of the proposed model in comparison with existing similar approaches.     

Soil-moisture estimation from TerraSAR-X data using neural networks

Early prediction of natural disasters like floods and landslides is essential for reasons of public safety. This can be attained by processing Synthetic-Aperture Radar (SAR) images and retrieving soil-moisture parameters. In this article, TerraSAR-X product images are investigated in combination with a water-cloud model based on the Shi semi-empirical model to determine the accuracy of soil-moisture parameter retrieval. SAR images were captured between January 2008 and September 2010 in the vicinity of the city Maribor, Slovenia, at different incidence angles. The water-cloud model provides acceptable estimated soil-moisture parameters at bare or scarcely vegetated soil areas. However, this model is too sensitive to speckle noise; therefore, a pre-processing step for speckle-noise reduction is carried out. Afterwards, self-organizing neural networks (SOM) are used to segment the areas at which the performance of this model is poor, and at the same time neural networks are also used for a more accurate approximation of model parameters’ values. Ground-truth is measured using the Pico64 sensor located on the field, simultaneously with capturing SAR images, in order to enable the comparison and validation of the obtained results. Experimental results show that the proposed method outperforms the water-cloud model accuracy over all incidence angles.     

Stem cell motion-tracking by using deep neural networks with multi-output

Neural Computing and Applications - The aim of automated stem cell motility analysis is reliable processing and evaluation of cell behaviors such as translocation, mitosis, death, and so on. Cell...     

Lifetime prediction using accelerated test data and neural networks

In this paper, a concept for the lifetime prediction of novel materials in civil engineering is presented. The approach does not require experiments over the structural lifetime and solves the problems of limited data and limited mechanical and physical insight in initial stages of investigation. Specifically, a combination of accelerated life testing with a neural network solution for function approximation over the time scale is proposed. The capabilities of the concept are demonstrated by a numerical example for verification purposes and a practical application for predicting the lifetime of textile reinforced concrete specimens at service load.     

Extraction rice-planted areas by RADARSAT data using neural networks

A classification technique using the neural networks has recently been developed. We apply a neural network of learning vector quantization (LVQ) to classify remote-sensing data, including microwave and optical sensors, for the estimation of a rice-planted area. The method has the capability of nonlinear discrimination, and the classification function is determined by learning. The satellite data were observed before and after planting rice in 1999. Three sets of RADARSAT and one set of SPOT/HRV data were used in Higashi–Hiroshima, Japan. Three RADARSAT images from April to June were used for this study. The LVQ classification was applied the RADARSAT and SPOT to evaluate the estimate of the area of planted-rice. The results show that the true production rate of the rice-planted area estimation of RADASAT by LVQ was approximately 60% compared with that of SPOT by LVQ. It is shown that the present method is much better than the SAR image classification by the maximum likelihood method.     

Classification of remotely-sensed image data using artificial neural networks

Abstract

Abstract. Artificial neural networks have been used recently for speech and character recognition. Their application for the classification of remotely-sensed images is reported in this Letter. Remotely sensed image data are usually large in size and spectral overlaps among classes of ground objects are common. This results in low convergence performance of the Back-Propagation Algorithm in a neural network classifier. A Blocked Back-Propagation (BB-P) algorithm was proposed arid described in this Letter. It improved convergence performance and classification accuracy.     

Training neural networks on high-dimensional data using random projection

Pattern Analysis and Applications - Training deep neural networks (DNNs) on high-dimensional data with no spatial structure poses a major computational problem. It implies a network architecture...     

An efficient approach to determine cell formation,cell layout and intracellular machine sequence in cellular manufacturing systems

Cellular manufacturing systems (CMS) are used to improve production flexibility and efficiency. They involve the identification of part families and machine cells so that intercellular movement is minimized and the utilization of the machines within a cell is maximized. Previous research has focused mainly on cell formation problems and their variants; however, only few articles have focused on more practical and complicated problems that simultaneously consider the three critical issues in the CMS-design process, i.e., cell formation, cell layout, and intracellular machine sequence. In this study, a two-stage mathematical programming model is formulated to integrate the three critical issues with the consideration of alternative process routings, operation sequences, and production volume. Next, because of the combinatorial nature of the above model, an efficient tabu search algorithm based on a generalized similarity coefficient is proposed. Computational results from test problems show that our proposed model and solution approach are both effective and efficient. When compared to the mathematical programming approach, which takes more than 112 h (LINGO) and 1139 s (CPLEX) to solve a set of ten test instances, the proposed algorithm can produce optimal solutions for the same set of test instances in less than 12 s.     

An Electromagnetism-like algorithm for cell formation and layout problem

Implementation of cellular manufacturing systems (CMS) is thriving among manufacturing companies due to many advantages that are attained by applying this system. In this study CMS formation and layout problems are considered. An Electromagnetism like (EM-like) algorithm is developed to solve the mentioned problems. In addition the required modifications to make EM-like algorithm applicable in these problems are mentioned. A heuristic approach is developed as a local search method to improve the quality of solution of EM-like. Beside in order to examine its performance, it is compared with two other methods. The performance of EM-like algorithm with proposed heuristic and GA are compared and it is demonstrated that implementing EM-like algorithm in this problem can improve the results significantly in comparison with GA. In addition some statistical tests are conducted to find the best performance of EM-like algorithm and GA due to their parameters. The convergence diagrams are plotted for two problems to compare the convergence process of the algorithms. For small size problems the performances of the algorithms are compared with an exact algorithm (Branch & Bound).     

The sustainable cell formation problem: manufacturing cell creation with machine modification costs

An approach for manufacturing cell formation with machine modification is presented. In cell formation it is often important in practice to be able to reassign parts to additional machine types in order to create better cell configurations. This involves extending the set of parts that certain individual machines can process. Such extensions may be cheaper than simply purchasing additional machines. Thus, there is the possibility of machine modification to reduce inter-cell travel. The cost of such modifications must be balanced by the consequent reduction in inter-cell travel cost. The extended machine cell formation problem to be described involves the specification of which individual machines should be modified to enable them to process additional part types, part-machine assignment, and the grouping of individual machines for cell formation. The objective is to minimize the sum of the machine modification costs and the inter-cell travel. We call this the sustainable cell formation problem (SCFP). As far as the authors are aware, there have not been any solution procedures for this important problem reported in the open literature. It is our purpose to fill this gap by presenting a mixed integer programming model of the SCFP. We also propose and analyze greedy and tabu search heuristics for the design of large-scale systems related to the SCFP. Computational experience with the solution procedures indicates that they are likely to be useful additions to the production engineer's toolkit.     

Principal component analysis of fuzzy data using autoassociative neural networks

This paper describes an extension of principal component analysis (PCA) allowing the extraction of a limited number of relevant features from high-dimensional fuzzy data. Our approach exploits the ability of linear autoassociative neural networks to perform information compression in just the same way as PCA, without explicit matrix diagonalization. Fuzzy input values are propagated through the network using fuzzy arithmetics, and the weights are adjusted to minimize a suitable error criterion, the inputs being taken as target outputs. The concept of correlation coefficient is extended to fuzzy numbers, allowing the interpretation of the new features in terms of the original variables. Experiments with artificial and real sensory evaluation data demonstrate the ability of our method to provide concise representations of complex fuzzy data.     

Manufacturing cell formation in the presence of flexible cell locations and material transporters

The effect of cell locations and material transporters in the formation of manufacturing cells is investigated in this paper. Automated guided vehicles (AGVs) using a tandem configuration are considered and a first-come-first-served (FCFS) principle is applied for transporting the material between machines or between the input/output (I/O) and a machine. Using the time taken to perform material transfers as a suitable measure, a polynomial programming model is developed for the problem. As the model can be shown strongly NP-hard, a higher-level heuristic algorithm based upon a concept known as ‘tabu search’ is presented. An example problem is solved to further demonstrate that cell locations indeed have a significant impact when material transfers are used in the design of manufacturing cells.