Abstract
Analytics applications are becoming indispensable in today’s business landscape. Greater data availability from self-monitoring production equipment allows firms to empower individual workers on the shop-floor with powerful decision support solutions. To explore the potential of such solutions, we replicate an important manual leak detection process from high-tech composite manufacturing and augment the system with highly sensitive sensors. Based on this setup we illustrate the main steps and major challenges in developing and instantiating a predictive decision support system. By establishing a scalable and generic feature generation approach as well as leveraging techniques from statistical learning, we are able to improve the forecasts of the leak position by almost 90%. Recognizing that mere forecast information cannot be evaluated with respect to business value, we subsequently embed the problem in an analysis of the underlying searcher path problem. We compare predictive and prescriptive search policies against simple benchmark rules. The data-supported policies dramatically reduce the median as well as the variability of the search time. Based on these findings we posit that prescriptive analytics can and should play a greater role in assisting manual labor in manufacturing environments.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
The problem seems to be suited for application spatial regression techniques. However, this approach requires the availability of independent variables over the whole search space. In our experiment setup we only record sensor readings at the edges of the mold. Furthermore, Tobler’s law of spatial auto-correlation (Tobler 1970) is violated in the experimental data: In each run there is a single leak and thus a leak at a given point has no direct effect on the probability of a leak occurring in neighboring positions. Hence, classic spatial regression approaches such as Kriging or geographically weighted regression can not be applied for the problem at hand.
The alternative formulation of maximizing the likelihood of detection is not applicable in our manufacturing scenario.
Another difference to this canonical formulation is the absence of step-level probabilities due to our point forecasts.
References
Aburto L, Weber R (2007) Improved supply chain management based on hybrid demand forecasts. Appl Soft Comput 7(1):136–144
Angalakudati M, Balwani S, Calzada J, Chatterjee B, Perakis G, Raad N, Uichanco J (2014) Business analytics for flexible resource allocation under random emergencies. Manag Sci 60(6):1552–1573
Aviv Y (2007) On the benefits of collaborative forecasting partnerships between retailers and manufacturers. Manag Sci 53(5):777–794
Basili VR (1996) The role of experimentation in software engineering: past, current, and future. In: Proceedings of the 18th international conference on software engineering. IEEE Computer Society, Berlin, Germany, pp 442–449
Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305
Bergstra J, Bardenet R, Bengio Y, Kégl B (2011) Algorithms for hyper-parameter optimization. In: Proceedings of neural information processing systems 24 (NIPS2011), pp 2546–2554
Beutel AL, Minner S (2012) Safety stock planning under causal demand forecasting. Int J Prod Econ 140(2):637–645
Carbonneau R, Laframboise K, Vahidov R (2008) Application of machine learning techniques for supply chain demand forecasting. Eur J Oper Res 184(3):1140–1154
Chae BK, Olson DL (2013) Business analytics for supply chain: a dynamic-capabilities framework. Int J Inf Technol Decis Mak 12(01):9–26
Chen M-C, Huang C-L, Chen K-Y, Wu H-P (2005) Aggregation of orders in distribution centers using data mining. Expert Syst Appl 28(3):453–460
Choudhary AK, Harding JA, Tiwari MK (2008) Data mining in manufacturing: a review based on the kind of knowledge. J Intell Manuf 20(5):501–521
Cui R, Allon G, Bassamboo A, Van Mieghem JA (2015) Information sharing in supply chains: an empirical and theoretical valuation. Manag Sci 61(11):2803–2824
Dieulle L, Bérenguer C, Grall A, Roussignol M (2003) Sequential condition-based maintenance scheduling for a deteriorating system. Eur J Oper Res 150(2):451–461
Domingos P (2012) A few useful things to know about machine learning. Commun ACM 55(10):78–87
Eickemeyer SC, Herde F, Irudayaraj P, Nyhuis P (2014) Decision models for capacity planning in a regeneration environment. Int J Prod Res 52(23):7007–7026
Foresee FD, Hagan MT (1997) Gauss–Newton approximation to Bayesian learning. In: International conference on neural networks, vol 3. IEEE, New York, pp 1930–1935
Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38(4):367–378
Friedman J, Hastie T, Tibshirani R (2001) Springer series in statistics, vol 1. The elements of statistical learning. Springer, Berlin
Galton F (1886) Regression towards mediocrity in hereditary stature. J Anthropol Inst G B Irel 15:246–263
Grabocka J, Wistuba M, Schmidt-Thieme L (2015) Scalable classification of repetitive time series through frequencies of local polynomials. IEEE Trans Knowl Data Eng 27(6):1683–1695
Grall A, Bérenguer C, Dieulle L (2002) A condition-based maintenance policy for stochastically deteriorating systems. Reliab Eng Syst Saf 76(2):167–180
Guosheng H, Guohong Z (2008) Comparison on neural networks and support vector machines in suppliers’ selection. J Syst Eng Electron 19(2):316–320
Heimbach I, Kostyra DS, Hinz O (2015) Marketing automation. Bus Inf Syst Eng 57(2):129
Hevner AR, March ST, Park J, Ram S (2004) Design science in information systems research. MIS Q Manag Inf Syst 28(1):75–105
Ho J-W, Fang C-C (2013) Production capacity planning for multiple products under uncertain demand conditions. Int J Prod Econ 141(2):593–604
Hothorn T, Hornik K, Zeileis A (2006) Unbiased recursive partitioning: a conditional inference framework. J Comput Graph Stat 15(3):651–674
Huang T, Van Mieghem JA (2014) Clickstream data and inventory management: model and empirical analysis. Prod Oper Manag 23(3):333–347
Jane C-C, Laih Y-W (2005) A clustering algorithm for item assignment in a synchronized zone order picking system. Eur J Oper Res 166(2):489–496
Karabuk S, Wu DS (2003) Coordinating strategic capacity planning in the semiconductor industry. Oper Res 51(6):839–849
Létourneau S, Famili F, Matwin S (1999) Data mining to predict aircraft component replacement. IEEE Intell Syst 14(6):59–66
Li X, Olafsson S (2005) Discovering dispatching rules using data mining. J Sched 8(6):515–527
Lustig I, Dietrich B, Johnson C, Dziekan C (2010) The Analytics Journey: an IBM view of the structured data analysis landscape: descriptive, predictive and prescriptive analytics. Anal Mag 11–18. http://www.analytics-magazine.org/november-december-2010/54-the-analytics-journey
Manyika J, Chui M, Brown B, Bughin J (2011) Big data: the next frontier for innovation, competition, and productivity. Technical report. McKinsey Global Institute, Chicago
Moro S, Cortez P, Rita P (2014) A data-driven approach to predict the success of bank telemarketing. Decis Support Syst 62:22–31
Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81–106
Raheja D, Llinas J, Nagi R, Romanowski C (2006) Data fusion/data mining-based architecture for condition-based maintenance. Int J Prod Res 44(14):2869–2887
Rasmussen CE (2006) Gaussian processes for machine learning. MIT Press, New York
Reif R, Günthner WA (2009) Pick-by-vision: augmented reality supported order picking. Vis Comput 25(5–7):461–467
Reutterer T, Hornik K, March N, Gruber K (2016) A data mining framework for targeted category promotions. J Bus Econ 1–22
Schwerdtfeger B, Reif R, Günthner WA, Klinker G (2011) Pick-by-vision: there is something to pick at the end of the augmented tunnel. Virtual Real 15(2–3):213–223
Shearer C (2000) The CRISP-DM model: the new blueprint for data mining. J data warehouse 5:13–22
Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222
Song C, Guan X, Zhao Q, Ho Y-C (2005) Machine learning approach for determining feasible plans of a remanufacturing system. IEEE Trans Autom Sci Eng 2(3):262–275
Stein N, Flath C (2017) Applying data science for shop-floor performance prediction. In: Proceedings of the 25th European conference on information systems (ECIS 2017)
Tan B (1998) Effects of variability on the due-time performance of a continuous materials flow production system in series. Int J Prod Econ 54(1):87–100
Tobler WR (1970) A computer movie simulating urban growth in the detroit region. Econ Geogr 46(sup1):234–240
Trummel K, Weisinger J (1986) Technical note—the complexity of the optimal searcher path problem. Oper Res 34(2):324–327
Tseng T-L, Huang C-C, Jiang F, Ho JC (2006) Applying a hybrid data-mining approach to prediction problems: a case of preferred suppliers prediction. Int J Prod Res 44(14):2935–2954
Wang K-J, Chen J, Lin Y-S (2005) A hybrid knowledge discovery model using decision tree and neural network for selecting dispatching rules of a semiconductor final testing factory. Prod Plan Control 16(7):665–680
Williams C, Summerscales J, Grove S (1996) Resin infusion under flexible tooling (RIFT): a review. Compos Part A Appl Sci Manuf 27(7):517–524
Wu D (2009) Supplier selection: a hybrid model using DEA, decision tree and neural network. Expert Syst Appl 36(5):9105–9112
Wu S, Akbarov A (2011) Support vector regression for warranty claim forecasting. Eur J Oper Res 213(1):196–204
Yan X, Zhang C, Zhang S (2003) Toward databases mining: pre-processing collected data. Appl Artif Intell 17(5–6):545–561
Yu L, Wang S, Lai KK (2006) An integrated data preparation scheme for neural network data analysis. IEEE Trans Knowl Data Eng 18(2):217–230
Zhang S, Zhang C, Yang Q (2003) Data preparation for data mining. Appl Artif Intell 17(5–6):375–381
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Stein, N., Meller, J. & Flath, C.M. Big data on the shop-floor: sensor-based decision-support for manual processes. J Bus Econ 88, 593–616 (2018). https://doi.org/10.1007/s11573-017-0890-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11573-017-0890-4