Statistical tolerance allocation design considering form errors based on rigid assembly simulation and deep Q-network

Consideration of form errors involves real machining features in tolerance modeling but increases uncertainties in functional requirement estimation, when tackling the trade-off between the cost and precision performance. In this paper, a statistical tolerance allocation method is presented to solve this problem. First of all, a top-down stepwise designing procedure is designed for complex products, and a combination of Jacobian matrix and Skin Model Shapes is applied in modeling the mechanical joints. Then, rigid assembly simulations of point-based surfaces are further advanced to provide an accurate estimation of the assembly state, through considering physical constraints and termination conditions. A mini-batch gradient descent method and a backtracking strategy are also proposed to promote computational efficiency. Finally, a deep Q-network is implemented in optimal computation after characterizing the systematic state, action domain, and reward function. The general tolerance scheme is then achieved using the trained Q-network. The results of 6 experiments each with 200 samples show the proposed method is capable of assessing tolerance schemes with 35.2% and 47.2% lower manufacturing costs and 16.7% and 28.3% higher precision maintenance on average than conventional particle swarm optimization and Monte Carlo method respectively.

[1]  Yue Wang,et al.  Tolerance Allocations on Products: A Life Cycle Engineering Perspective , 2019, Procedia CIRP.

[2]  R. N. Roth,et al.  Genetic algorithms in statistical tolerancing , 1999 .

[3]  M. N. Islam,et al.  Functional dimensioning and tolerancing software for concurrent engineering applications , 2004, Comput. Ind..

[4]  Arumugam Nallanathan,et al.  Cooperative Deep Reinforcement Learning for Multiple-group NB-IoT Networks Optimization , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  M. Boyer,et al.  Modeling Spaces for Toleranced Objects , 1991, Int. J. Robotics Res..

[6]  Sandro Wartzack,et al.  Skin Model Shapes: Offering New Potentials for Modelling Product Shape Variability , 2015 .

[7]  Xinmin Lai,et al.  A small displacement torsor model for 3D tolerance analysis of conical structures , 2015 .

[8]  Bernard Anselmetti.  Generation of functional tolerancing based on positioning features , 2006, Comput. Aided Des..

[9]  Satish C. Jain,et al.  Advanced optimal tolerance design of mechanical assemblies with interrelated dimension chains and process precision limits , 2005, Comput. Ind..

[10]  R. Sutton.  Introduction: The Challenge of Reinforcement Learning , 1992 .

[11]  Sanghyun Park,et al.  DQN-based OpenCL workload partition for performance optimization , 2019, The Journal of Supercomputing.

[12]  Chun Zhang,et al.  Integrated tolerance optimisation with simulated annealing , 1993 .

[13]  Denis Teissandier,et al.  A computer aided tolerancing model: proportioned assembly clearance volume , 1999, Comput. Aided Des..

[14]  Maroua Ghali,et al.  Integrated CAD tolerancing model based on difficulty coefficient evaluation and Lagrange multiplier , 2019 .

[15]  Massimiliano Marziale,et al.  A review of two models for tolerance analysis of an assembly: vector loop and matrix , 2009 .

[16]  N. Jawahar,et al.  Optimal Pareto front for manufacturing tolerance allocation model , 2017 .

[17]  Sergey Levine,et al.  Guided Policy Search , 2013, ICML.

[18]  Wilma Polini.  Taxonomy of models for tolerance analysis in assembling , 2012 .

[19]  Alain Desrochers,et al.  A CAD/CAM representation model applied to tolerance transfer methods , 2003 .

[20]  Polini Wilma,et al.  Manufacturing Signature for Tolerance Analysis , 2015 .

[21]  Serge Samper,et al.  Tolerance Analysis and Synthesis by Means of Deviation Domains, Axi-Symmetric Cases , 2007 .

[22]  Rikard Söderberg,et al.  Variation Simulation for Composite Parts and Assemblies Including Variation in Fiber Orientation and Thickness , 2014 .

[23]  Peng Wang,et al.  An effective strategy for improving the precision and computational efficiency of statistical tolerance optimization , 2017 .

[24]  Wojciech Samek,et al.  Analyzing Neuroimaging Data Through Recurrent Deep Learning Models , 2018, Front. Neurosci..

[25]  M. Siva Kumar,et al.  Optimum tolerance synthesis for complex assembly with alternative process selection using Lagrange multiplier method , 2009 .

[26]  Yanlong Cao,et al.  A comprehensive review of tolerance analysis models , 2018 .

[27]  Jean-Yves Dantan,et al.  Worst-case and statistical tolerance analysis based on quantified constraint satisfaction problems and Monte Carlo simulation , 2009, Comput. Aided Des..

[28]  Wei Wang,et al.  Variable coefficients reciprocal squared model based on multi-constraints of aircraft assembly tolerance allocation , 2016 .

[29]  P. K. Jain,et al.  A genetic algorithm-based solution to optimal tolerance synthesis of mechanical assemblies with alternative manufacturing processes: focus on complex tolerancing problems , 2004 .

[30]  Xing Zhang,et al.  An Improved Deep Q-Learning for Intelligent Transmitter Control System , 2019, Lecture Notes in Electrical Engineering.

[31]  C. R. Liu,et al.  Review of dimensioning and tolerancing: representation and processing , 1991, Comput. Aided Des..

[32]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[33]  Kenneth W. Chase,et al.  A survey of research in the application of tolerance analysis to the design of mechanical assemblies , 1991 .

[34]  Sandro Wartzack,et al.  Evaluation of geometric tolerances and generation of variational part representatives for tolerance analysis , 2015 .

[35]  P. V. Mohanram,et al.  Cost optimization of process tolerance allocation-a tree based approach , 2007 .

[36]  Spencer P. Magleby,et al.  Generalized 3-D tolerance analysis of mechanical assemblies with small kinematic adjustments , 1998 .

[37]  Jean-Yves Dantan,et al.  Tolerance synthesis: quantifier notion and virtual boundary , 2005, Comput. Aided Des..

[38]  Joshua U. Turner,et al.  Variational solid modeling for tolerance analysis , 1993, IEEE Computer Graphics and Applications.

[39]  Herbert B. Voelcker,et al.  The current state of affairs in dimensional tolerancing: 1997 , 1998 .

[40]  Tangbin Xia,et al.  State space modeling of multi-scale variation propagation in machining process using matrix model , 2017, 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM).

[41]  W. Ghie,et al.  Statistical and Deterministic Tolerance Analysis and Synthesis Using a Unified Jacobian-Torsor Model , 2002 .

[42]  K. Sankaranarayanasamy,et al.  Optimal tolerance design of assembly for minimum quality loss and manufacturing cost using metaheuristic algorithms , 2009 .

[43]  P. Dayan,et al.  Reinforcement learning: The Good, The Bad and The Ugly , 2008, Current Opinion in Neurobiology.

[44]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[45]  Daniel E. Whitney,et al.  Representation of geometric variations using matrix transforms for statistical tolerance analysis in assemblies , 1994 .

[46]  Sandro Wartzack,et al.  Novel approaches for the assembly simulation of rigid Skin Model Shapes in tolerance analysis , 2018, Comput. Aided Des..

[47]  Wilma Polini,et al.  Manufacturing signature in jacobian and torsor models for tolerance analysis of rigid parts , 2017 .

[48]  Y. S. Hong,et al.  A comprehensive review of tolerancing research , 2002 .

[49]  Haiping Zhu,et al.  A novel tolerance analysis for mechanical assemblies based on Convex Method and non-probabilistic set theory , 2016 .

[50]  Sandro Wartzack,et al.  From tolerance allocation to tolerance-cost optimization: a comprehensive literature review , 2020, The International Journal of Advanced Manufacturing Technology.

[51]  Carl E. Rasmussen,et al.  PILCO: A Model-Based and Data-Efficient Approach to Policy Search , 2011, ICML.

[52]  Cari M. Whyne,et al.  Seglearn: A Python Package for Learning Sequences and Time Series , 2018, J. Mach. Learn. Res..

[53]  Long Ji Lin,et al.  Self-improving reactive agents based on reinforcement learning, planning and teaching , 1992, Machine Learning.

[54]  P K Jain,et al.  Comparative study of genetic algorithm and simulated annealing for optimal tolerance design formulated with discrete and continuous variables , 2005 .

[55]  G. Mauri,et al.  Computational Methods for Resting-State EEG of Patients With Disorders of Consciousness , 2019, Front. Neurosci..

[56]  Marc Peter Deisenroth,et al.  Deep Reinforcement Learning: A Brief Survey , 2017, IEEE Signal Processing Magazine.

[57]  Yanru Zhang,et al.  The quality control method for remanufacturing assembly based on the Jacobian-torsor model , 2015 .

[58]  L. F. Hauglund,et al.  Least Cost Tolerance Allocation for Mechanical Assemblies with Automated Process Selection , 1990 .

[59]  Weikuan Jia,et al.  Applications of asynchronous deep reinforcement learning based on dynamic updating weights , 2018, Applied Intelligence.

[60]  Quirico Semeraro,et al.  Machining Planning for Tolerance Synthesis , 2003 .

[61]  Yan Wang,et al.  A closed-form method for statistical tolerance allocation considering quality loss and different kinds of manufacturing cost functions , 2017 .

[62]  Yanlong Cao,et al.  Assembly tolerance analysis based on the Jacobian model and skin model shapes , 2019 .

[63]  Robert Babuska,et al.  Experience Selection in Deep Reinforcement Learning for Control , 2018, J. Mach. Learn. Res..

[64]  Wilma Polini,et al.  Manufacturing signature in variational and vector-loop models for tolerance analysis of rigid parts , 2017 .

[65]  P. Asokan,et al.  Genetic-algorithm-based optimal tolerance allocation using a least-cost model , 2004 .

[66]  H. P. Peng,et al.  Concurrent optimal allocation of design and process tolerances for mechanical assemblies with interrelated dimension chains , 2008 .

[67]  Byeng D. Youn,et al.  Variation Propagation Analysis on Compliant Assemblies Considering Contact Interaction , 2007 .

[68]  Joshua U. Turner,et al.  Review of statistical approaches to tolerance analysis , 1995, Comput. Aided Des..

[69]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[70]  Joseph K. Davidson,et al.  Comparison of Two Similar Mathematical Models for Tolerance Analysis: T-Map and Deviation Domain , 2013 .

[71]  Haipeng Yao,et al.  Blockchain-Based Software-Defined Industrial Internet of Things: A Dueling Deep ${Q}$ -Learning Approach , 2019, IEEE Internet of Things Journal.

[72]  Xiaoyun Liao,et al.  Non-linear dimensional variation analysis for sheet metal assemblies by contact modeling , 2007 .

[73]  Bernard Anselmetti.  Part optimization and tolerances synthesis , 2010 .

[74]  Sandro Wartzack,et al.  Approaches for the assembly simulation of skin model shapes , 2015, Comput. Aided Des..

[75]  Gaurav Ameta,et al.  Comparison of Spatial Math Models for Tolerance Analysis: Tolerance-Maps, Deviation Domain, and TTRS , 2011, J. Comput. Inf. Sci. Eng..

[76]  Joseph K. Davidson,et al.  Tolerance-Maps to Model Composite Positional Tolerancing for Patterns of Features , 2018, J. Comput. Inf. Sci. Eng..

[77]  A. Saravanan,et al.  Concurrent optimal allocation of geometric and process tolerances based on the present worth of quality loss using evolutionary optimisation techniques , 2017 .

[78]  Peter Stone,et al.  Deep Recurrent Q-Learning for Partially Observable MDPs , 2015, AAAI Fall Symposia.

[79]  Peter Gust,et al.  Analysis of Approaches of Tolerance Allocation regarding to Economic Efficiency , 2019 .

[80]  Kuei-Yuan Chan,et al.  Kinematic error analysis and tolerance allocation of cycloidal gear reducers , 2018, Mechanism and Machine Theory.

[81]  Tzu-Chieh Hung,et al.  Multi-objective design and tolerance allocation for single- and multi-level systems , 2013, J. Intell. Manuf..

[82]  A. Clément,et al.  A dimensioning and tolerancing assistance model for CAD/CAM systems , 1994 .

[83]  Sandro Wartzack,et al.  From solid modelling to skin model shapes: Shifting paradigms in computer-aided tolerancing , 2014 .