A human-assisted knowledge extraction method for machining operations

Abstract This paper deals with a human-assisted knowledge extraction method to extract “if…then…” rules from a small set of machining data. The presented method utilizes both probabilistic reasoning and fuzzy logical reasoning to benefit from the machining data and from the judgment and preference of a machinist. Using the extracted rules, one can determine the values of operational parameters (feed, cutting velocity, etc.) to ensure the desired machining performance (keep surface roughness within the stipulated range (e.g., moderate)). Applying the presented method in a real-life machining knowledge extraction situation and comparing it with the inductive learning based knowledge extraction method (i.e., ID3), the usefulness of the method is demonstrated. As the concept of manufacturing automation is shifting toward “how to support humans by computers”, the presented method provides some valuable hints to the developers of futuristic computer integrated manufacturing systems.

[1]  Witold Pedrycz,et al.  Fuzzy descriptive models: an interactive framework of information granulation [ECG data] , 2002, IEEE Trans. Fuzzy Syst..

[2]  L. Zadeh.  Toward a Perception-Based Theory of Probabilistic Reasoning , 2000, Rough Sets and Current Trends in Computing.

[3]  Jeremy E. Oakley,et al.  Probability is perfect, but we can't elicit it perfectly , 2004, Reliab. Eng. Syst. Saf..

[4]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[5]  Henri Prade,et al.  What are fuzzy rules and how to use them , 1996, Fuzzy Sets Syst..

[6]  G. Klir,et al.  Fuzzy Measure Theory , 1993 .

[7]  Francisco Herrera,et al.  A fusion approach for managing multi-granularity linguistic term sets in decision making , 2000, Fuzzy Sets Syst..

[8]  P. Walley.  Statistical Reasoning with Imprecise Probabilities , 1990 .

[9]  A. M. M. Sharif Ullah,et al.  Manufacturing process performance prediction by integrating crisp and granular information , 2005, J. Intell. Manuf..

[10]  Derek A. Linkens,et al.  Rule-base self-generation and simplification for data-driven fuzzy models , 2004, Fuzzy Sets Syst..

[11]  Shaw Voon Wong,et al.  The development of an online knowledge-based expert system for machinability data selection , 2003, Knowl. Based Syst..

[12]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[13]  Jacek M. Zurada,et al.  Data-driven linguistic modeling using relational fuzzy rules , 2003, IEEE Trans. Fuzzy Syst..

[14]  P. Walley,et al.  Direct algorithms for checking consistency and making inferences from conditional probability assessments , 2004 .

[15]  Thomas Lukasiewicz,et al.  Weak nonmonotonic probabilistic logics , 2004, Artif. Intell..

[16]  P. Billingsley,et al.  Probability and Measure , 1980 .

[17]  Lotfi A. Zadeh,et al.  From imprecise to granular probabilities , 2005, Fuzzy Sets Syst..

[18]  Gert de Cooman,et al.  Updating beliefs with incomplete observations , 2003, Artif. Intell..

[19]  Bogomir Muršec,et al.  Integral model of selection of optimal cutting conditions from different databases of tool makers , 2003 .

[20]  László Monostori,et al.  AI and machine learning techniques for managing complexity, changes and uncertainties in manufacturing , 2003 .

[21]  Gert de Cooman,et al.  n-Monotone lower previsions , 2005, J. Intell. Fuzzy Syst..

[22]  Masahiro Higuchi,et al.  Virtual machinability data versus real machinability data and their use during manufacturing decion-making , 1998 .

[23]  A. Kaufmann,et al.  Introduction to fuzzy arithmetic : theory and applications , 1986 .

[24]  Didier Dubois,et al.  A new perspective on reasoning with fuzzy rules , 2002, Int. J. Intell. Syst..

[25]  Lotfi A. Zadeh,et al.  Precisiated Natural Language , 2007, Aspects of Automatic Text Analysis.

[26]  M. A. El Baradie,et al.  A fuzzy logic model for machining data selection , 1997 .

[27]  A. K. Balaji,et al.  Towards integration of hybrid models for optimized machining performance in intelligent manufacturing systems , 2003 .

[28]  Shaw Voon Wong,et al.  Generalized fuzzy model for metal cutting data selection , 1999 .

[29]  Lotfi A. Zadeh,et al.  Precisiated Natural Language (PNL) , 2004, AI Mag..

[30]  Bruce Tonn.  Imprecise probabilities and scenarios , 2005 .

[31]  ICHIRO KOBAYASHI,et al.  An Approach to a Dynamic System Simulation Based on Human Information Processing , 2002, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[32]  Michael Negnevitsky,et al.  Artificial Intelligence: A Guide to Intelligent Systems , 2001 .

[33]  M A El Baradie,et al.  Surface Roughness Model for Turning Grey Cast Iron (154 BHN) , 1993 .

[34]  Lotfi A. Zadeh,et al.  Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic , 1997, Fuzzy Sets Syst..

[35]  Didier Dubois,et al.  Fuzzy sets and systems ' . Theory and applications , 2007 .

[36]  H.J.J. Kals,et al.  Information management and process integration in manufacturing , 2002 .

[37]  S. Li,et al.  FUZZY CLUSTERING FOR AUTOMATED TOOL CONDITION MONITORING IN MACHINING , 1996 .

[38]  H.J.J. Kals,et al.  Information Management in Process Planning , 1999 .