Complex networks of material flow in manufacturing and logistics: Modeling, analysis, and prediction using stochastic block models

Abstract Modeling complex systems as networks of interacting elements has gained increased attention in recent years. So far, network modeling in manufacturing and logistics has often focused on the description of system properties. In the data-driven world of smart manufacturing, creating material flow network models becomes a lot easier due to the ubiquitous availability of shop floor and transportation data. At the same time, these highly flexible and continuously changing smart manufacturing systems become less predictive and thus less controllable. This article investigates how the stochastic block model (SBM), a network model with a stochastic description of interconnections, can be applied to model and predict material flows in manufacturing systems. We show how to utilize its properties to forecast the dynamic development of the structure of such systems. The complete process from network modeling using material flow data to the prediction of the future development of the network is demonstrated. Different SBM variants are tested using six company data sets and evaluated in competition with classical machine learning methods for prediction. Our results show that selected SBM variants achieve the best performance in prediction in most scenarios and thus have the potential to play an important role in the management of future dynamic manufacturing systems.

[1]  Till Becker,et al.  Stochastic block models: A comparison of variants and inference methods , 2019, PloS one.

[2]  Till Becker,et al.  Towards an Understanding of the Relation between Topological Characteristics and Dynamic Behavior in Manufacturing Networks , 2014 .

[3]  Tomomi Kito,et al.  The implications of automobile parts supply network structures: A complex network approach , 2014 .

[4]  Lawrence Carin,et al.  Stochastic Blockmodels meet Graph Neural Networks , 2019, ICML.

[5]  S. Shen-Orr,et al.  Network motifs: simple building blocks of complex networks. , 2002, Science.

[6]  Andrew Kusiak,et al.  Data-driven smart manufacturing , 2018, Journal of Manufacturing Systems.

[7]  Marc-Thorsten Hütt,et al.  The impact of network connectivity on performance in production logistic networks , 2012 .

[8]  Marc-Thorsten Hütt,et al.  Graph coloring dynamics: A simple model scenario for distributed decisions in production logistics , 2010 .

[9]  Hao Liao,et al.  Predicting missing links via correlation between nodes , 2014, ArXiv.

[10]  J. King,et al.  Machine-component group formation in group technology: review and extension , 1982 .

[11]  Wolfgang Nejdl,et al.  Node Representation Learning for Directed Graphs , 2018, ECML/PKDD.

[12]  Herbert Kopfer,et al.  Collaborating freight forwarding enterprises , 2006, OR Spectr..

[13]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[14]  Till Becker,et al.  Automated Generation of Material Flow Network Models with Cluster Structures Using Random Walks , 2018 .

[15]  Dirk Helbing,et al.  Flow control by periodic devices: a unifying language for the description of traffic, production, and metabolic systems , 2011 .

[16]  Mark E. J. Newman,et al.  The Structure and Function of Complex Networks , 2003, SIAM Rev..

[17]  Albert-László Barabási,et al.  Statistical mechanics of complex networks , 2001, ArXiv.

[18]  Tiago P. Peixoto.  Model selection and hypothesis testing for large-scale network models with overlapping groups , 2014, ArXiv.

[19]  Ciro Cattuto,et al.  Detecting the Community Structure and Activity Patterns of Temporal Networks: A Non-Negative Tensor Factorization Approach , 2013, PloS one.

[20]  Megha Khosla,et al.  A Comparative Study for Unsupervised Network Representation Learning , 2019 .

[21]  Michael G. H. Bell,et al.  Topological Structure of Manufacturing Industry Supply Chain Networks , 2018, Complex..

[22]  Aaron Clauset,et al.  Evaluating Overfit and Underfit in Models of Network Community Structure , 2018, IEEE Transactions on Knowledge and Data Engineering.

[23]  Nino Antulov-Fantulin,et al.  Statistical embedding for directed graphs , 2019, ArXiv.

[24]  Patrick Charpentier,et al.  From Spatio-Temporal Data to Manufacturing System Model , 2014 .

[25]  Nilay Shah,et al.  Logistical network design with robustness and complexity considerations , 2007 .

[26]  Dazhong Wu,et al.  Cloud manufacturing: Strategic vision and state-of-the-art☆ , 2013 .

[27]  Andrew Kusiak,et al.  Service manufacturing: Basic concepts and technologies , 2019, Journal of Manufacturing Systems.

[28]  Tiago P. Peixoto.  Hierarchical block structures and high-resolution model selection in large networks , 2013, ArXiv.

[29]  S. Wasserman,et al.  Stochastic a posteriori blockmodels: Construction and assessment , 1987 .

[30]  Till Becker,et al.  Forecasting Changes in Material Flow Networks with Stochastic Block Models , 2019 .

[31]  Dimitris Mourtzis,et al.  Development of methods and tools for the design and operation of manufacturing networks for mass customisation , 2016 .

[32]  Serguei Saavedra,et al.  Strong contributors to network persistence are the most vulnerable to extinction , 2011, Nature.

[33]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[34]  Lihui Wang,et al.  Global production networks: Design and operation , 2019, CIRP Annals.

[35]  Pingyu Jiang,et al.  Dynamic scheduling in RFID-driven discrete manufacturing system by using multi-layer network metrics as heuristic information , 2019, J. Intell. Manuf..

[36]  Gesine Reinert,et al.  Estimating the number of communities in a network , 2016, Physical review letters.

[37]  Steve New,et al.  How automobile parts supply network structures may reflect the diversity of product characteristics and suppliers’ production strategies , 2015 .

[38]  Patrick Charpentier,et al.  Generation of an adaptive simulation driven by product trajectories , 2012, J. Intell. Manuf..

[39]  Peter Plapper,et al.  Lessons from social network analysis to Industry 4.0 , 2017 .

[40]  Philippa Pattison,et al.  Manufacturing Relations: An Empirical Study of the Organization of Production Across Multiple Networks , 2006, Organ. Sci..

[41]  M E J Newman,et al.  Community structure in social and biological networks , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[42]  Andrés Polo,et al.  Applying Social Network Analysis on Rural Manufacturing of the Savannah of Bogota , 2015 .

[43]  Fernando Berzal Galiano,et al.  A Survey of Link Prediction in Complex Networks , 2016, ACM Comput. Surv..

[44]  Peter Butala,et al.  Anomaly detection in shop floor material flow: A network theory approach , 2013 .

[45]  W. Zachary,et al.  An Information Flow Model for Conflict and Fission in Small Groups , 1977, Journal of Anthropological Research.

[46]  Suyu Liu,et al.  Clustering structure and logistics: A new framework for supply network analysis , 2013 .

[47]  M. Chandrasekharan,et al.  An ideal seed non-hierarchical clustering algorithm for cellular manufacturing , 1986 .

[48]  Hui Cheng,et al.  A network-based assessment approach for change impacts on complex product , 2012, J. Intell. Manuf..

[49]  Cristopher Moore,et al.  The Computer Science and Physics of Community Detection: Landscapes, Phase Transitions, and Hardness , 2017, Bull. EATCS.

[50]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[51]  Lilan Liu,et al.  Resource allocation and network evolution considering economics and robustness in manufacturing grid , 2011 .

[52]  Peter Butala,et al.  Discovering autonomous structures within complex networks of work systems , 2012 .

[53]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[54]  S. New,et al.  Towards capturing heterogeneity of supply network structures and their temporal transitions: an investigation of supply relationships in the Japanese automobile industry , 2015 .

[55]  Matteo Cinelli,et al.  A network perspective on the visualization and analysis of bill of materials , 2017 .

[56]  Till Becker,et al.  Stochastic Block Models as a Modeling Approach for Dynamic Material Flow Networks in Manufacturing and Logistics , 2018 .

[57]  Thomas Y. Choi,et al.  Structural investigation of supply networks: A social network analysis approach , 2011 .

[58]  Till Becker,et al.  Characterization of Cluster Structures in Material Flow Networks: A Network Approach☆ , 2016 .

[59]  Peter Butala,et al.  Decentralised network architecture for cloud manufacturing , 2017, Int. J. Comput. Integr. Manuf..

[60]  Tiago P. Peixoto.  Bayesian Stochastic Blockmodeling , 2017, Advances in Network Clustering and Blockmodeling.

[61]  S. N. Samy,et al.  A model for assessing the layout structural complexity of manufacturing systems , 2014 .

[62]  C. Robert Kenley,et al.  Reference architectures for smart manufacturing: A critical review , 2018, Journal of Manufacturing Systems.

[63]  Kathryn B. Laskey,et al.  Stochastic blockmodels: First steps , 1983 .

[64]  Marc-Thorsten Hütt,et al.  The elementary flux modes of a manufacturing system: a novel approach to explore the relationship of network structure and function , 2016 .

[65]  Cristopher Moore,et al.  Community detection, link prediction, and layer interdependence in multilayer networks , 2017, Physical review. E.

[66]  Peter Butala,et al.  Simulation study of large production network robustness in uncertain environment , 2015 .

[67]  Linyuan Lü,et al.  Predicting missing links via local information , 2009, 0901.0553.

[68]  Xun Xu,et al.  From cloud computing to cloud manufacturing , 2012 .

[69]  H. Wiendahl,et al.  Production in Networks , 2002 .

[70]  Botond Kádár,et al.  Enhanced control of complex production structures by tight coupling of the digital and the physical worlds , 2010 .

[71]  S. Strogatz.  Exploring complex networks , 2001, Nature.

[72]  Timothy Ravasi,et al.  From link-prediction in brain connectomes and protein interactomes to the local-community-paradigm in complex networks , 2013, Scientific Reports.

[73]  Emmanuel Abbe,et al.  Community detection and stochastic block models: recent developments , 2017, Found. Trends Commun. Inf. Theory.

[74]  Judit Mesterné Monostori,et al.  Robustness- and Complexity-oriented Characterization of Supply Networks’ Structures , 2016 .

[75]  Tiago P. Peixoto.  Nonparametric Bayesian inference of the microcanonical stochastic block model. , 2016, Physical review. E.

[76]  Zengwang Xu,et al.  Exploring the structure of the U.S. intercity passenger air transportation network: a weighted complex network approach , 2008 .

[77]  James Bailey,et al.  Information theoretic measures for clusterings comparison: is a correction for chance necessary? , 2009, ICML '09.

[78]  D. Wagner,et al.  Evaluation of the Applicability of Random Walks for Generation of Material Flow Network Models , 2017 .

[79]  Nariaki Nishino,et al.  Manufacturer's strategy in a sharing economy , 2017 .

[80]  Soundar Kumara,et al.  Complex Networks: An Engineering View , 2010, IEEE Circuits and Systems Magazine.

[81]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[82]  Alexandra Brintrup,et al.  Linking product and machine network structure using nested pattern analysis , 2014 .

[83]  Mark E. J. Newman,et al.  Stochastic blockmodels and community structure in networks , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[84]  Andrew Y. C. Nee,et al.  Complex networks in advanced manufacturing systems , 2017 .

[85]  Konstantin Avrachenkov,et al.  Cooperative Game Theory Approaches for Network Partitioning , 2017, COCOON.

[86]  Carliss Y. Baldwin,et al.  The Architecture of Transaction Networks: A Comparative Analysis of Hierarchy in Two Sectors , 2012 .

[87]  M. Newman.  Clustering and preferential attachment in growing networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[88]  P. Latouche,et al.  Model selection and clustering in stochastic block models based on the exact integrated complete data likelihood , 2015 .

[89]  Marc-Thorsten Hütt,et al.  A Comparison of Network Characteristics in Metabolic and Manufacturing Systems , 2012, LDIC.

[90]  Frederic Sala,et al.  Learning Mixed-Curvature Representations in Product Spaces , 2018, ICLR.

[91]  Till Becker,et al.  A Tool for an Analysis of the Dynamic Behavior of Logistic Systems with the Instruments of Complex Networks , 2018, LDIC.

[92]  Edoardo M. Airoldi,et al.  Mixed Membership Stochastic Blockmodels , 2007, NIPS.

[93]  Jian Pei,et al.  Asymmetric Transitivity Preserving Graph Embedding , 2016, KDD.

[94]  Peter Butala,et al.  Identifying the business and social networks in the domain of production by merging the data from heterogeneous internet sources , 2018, International Journal of Production Economics.

[95]  Peter Butala,et al.  Autonomous Work Systems in Manufacturing Networks , 2006 .

[96]  Jianhua Ruan,et al.  A novel link prediction algorithm for reconstructing protein-protein interaction networks by topological similarity , 2013, Bioinform..

[97]  Haiyan Huang,et al.  Review on statistical methods for gene network reconstruction using expression data. , 2014, Journal of theoretical biology.

[98]  Pingyu Jiang,et al.  A performance evaluation method for radio frequency identification–based tracking network of job-shop-type work-in-process material flows , 2013 .

[99]  Till Becker,et al.  Improvement Heuristics for Manufacturing System Design Using Complex Network Figures , 2014 .

[100]  Roger Guimerà,et al.  Missing and spurious interactions and the reconstruction of complex networks , 2009, Proceedings of the National Academy of Sciences.

[101]  Edward J.S. Hearnshaw,et al.  A complex network approach to supply chain network theory , 2013 .

[102]  Till Becker,et al.  Dynamics of resource sharing in production networks , 2015 .

[103]  Ray Y. Zhong,et al.  A big data approach for logistics trajectory discovery from RFID-enabled production data , 2015 .

[104]  Xun Xu,et al.  Development of a Hybrid Manufacturing Cloud , 2014 .

[105]  V. Latora,et al.  Complex networks: Structure and dynamics , 2006 .