Training and Application of Artificial Neural Networks with Incomplete Data

The paper describes a novel approach for learning and applying artificial neural network (ANN) models based on incomplete data. A basic novelty in this approach is not to replace the missing part of incomplete data but to train and apply ANN-based models in a way that they should be able to handle such situations. The root of the idea is inherited form the authors? earlier research for finding an appropriate input-output configuration of ANN models [16]. The introduced concept shows that it is worth purposely impairing the data used for learning to prepare the ANN model for handling incomplete data efficiently. The applicability of the proposed solution is demonstrated by the results of experimental runs with both artificial and real data. New experiments refer to the modelling and monitoring of cutting processes. Keywords: Neural Networks, Machine Learning, Applications to Manufacturing.

[1]  Michael I. Jordan,et al.  Learning from Incomplete Data , 1994 .

[2]  S.S. Rangwala,et al.  Learning and optimization of machining operations using computing abilities of neural networks , 1989, IEEE Trans. Syst. Man Cybern..

[3]  László Monostori,et al.  Automatic Input-Output Configuration and Generation of ANN-based Process Models and Their Application in Machining , 1999, IEA/AIE.

[4]  T. Warren Liao,et al.  A neural network approach for grinding processes: Modelling and optimization , 1994 .

[5]  Ed Anan Shetty,et al.  Literature , 1965, Science.

[6]  Martti Juhola,et al.  Treatment of missing data values in a neural network based decision support system for acute abdominal pain , 1998, Artif. Intell. Medicine.

[7]  László Monostori,et al.  Soft Computing and Hybrid AI Approaches to Intelligent Manufacturing , 1998, IEA/AIE.

[8]  Gerald Warnecke,et al.  Control of tolerances in turning by predictive control with neural networks , 1998, J. Intell. Manuf..

[9]  Fritz Klocke,et al.  Present Situation and Future Trends in Modelling of Machining Operations Progress Report of the CIRP Working Group ‘Modelling of Machining Operations’ , 1998 .

[10]  Giorgio Matteucci,et al.  Seasonal net carbon dioxide exchange of a beech forest with the atmosphere , 1996 .

[11]  Tom Tollenaere,et al.  SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.

[12]  László Monostori,et al.  A Step towards Intelligent Manufacturing: Modelling and Monitoring of Manufacturing Processes through Artificial Neural Networks , 1993 .

[13]  Tomasz Lenartowicz,et al.  Productivity Assessment of Multiple Retail Outlets , 1996 .

[14]  László Monostori,et al.  Hybrid, AI- and simulation-supported optimisation of process chains and production plants , 2001 .

[15]  László Monostori,et al.  Optimisation of Process Chains and Production Plants by Using a Hybrid-, AI-, and Simulation-Based Approach , 2001, IEA/AIE.

[16]  Sang-Gook Kim,et al.  Optimization of process parameters of injection molding with neural network application in a process simulation environment , 1994 .

[17]  M. E. Merchant.  AN INTERPRETIVE LOOK AT 20TH CENTURY RESEARCH ON MODELING OF MACHINING , 1998 .

[18]  László Monostori,et al.  Machine Learning Approaches to Manufacturing , 1996 .

[19]  László Monostori,et al.  Satisfying various requirements in different levels and stages of machining using one general ANN-based process model , 2000 .

[20]  Gerald M. Knapp,et al.  Acquiring, storing and utilizing process planning knowledge using neural networks , 1992, J. Intell. Manuf..

[21]  László Monostori,et al.  Optimisation of process chains and production plants using hybrid, AI- and simulation based general process models , 2001 .