Smart Machining Systems – Modelling, Monitoring and Informatics

Smart Machining Systems – Modelling, Monitoring and Informatics
اسم المؤلف
Kunpeng Zhu
التاريخ
13 مايو 2022
المشاهدات
549
التقييم
(لا توجد تقييمات)
Loading...

Smart Machining Systems – Modelling, Monitoring and Informatics
Kunpeng Zhu
Contents
1 Introduction to the Smart Machining System 1
1.1 The Development of Modern Manufacturing System 1
1.2 Modern Machining Technology 4
1.2.1 High Precision Machining . 4
1.2.2 High Speed Machining 5
1.2.3 Green Machining . 6
1.2.4 Smart Machining . 7
1.3 The Smart Machining System 7
1.3.1 Intelligent Process Planning 9
1.3.2 The Process Simulation and Optimization 9
1.3.3 The Machining Process Monitoring . 11
1.3.4 The Intelligent Control 12
1.3.5 The Database and Big Data Analytics 13
1.3.6 Smart Machine Tool . 13
1.4 The Trends of Smart Machining System . 15
References 16
2 Modeling of the Machining Process . 19
2.1 The Machining Process Modeling Methods 19
2.1.1 Modeling Based on Cutting Mechanics 20
2.1.2 Modeling Based on Machine Tool Vibration 20
2.1.3 Modeling Based on Numerical Simulation 20
2.1.4 Modeling Based on Measurement Information 21
2.1.5 Modeling Based on Artificial Intelligence (AI) 21
2.1.6 Modeling Method Combining Data and Cutting
Mechanics . 22
2.2 Principles of Chip Formation . 22
2.2.1 Chip Formation . 22
2.2.2 Mechanical Model of Chip Formation . 22
2.2.3 Divisions of Deformation Zones 25
2.3 Cutting Forces . 27
xixii Contents
2.3.1 Sources of Cutting Forces 27
2.3.2 Joint and Component Cutting Forces and Cutting
Powers 28
2.3.3 Empirical Models of Cutting Forces . 29
2.3.4 Affecting Factors of Cutting Forces 33
2.4 Cutting Heat and Temperatures . 36
2.4.1 Generation and Transfer of Cutting Heat . 36
2.4.2 Cutting Temperatures and Their Distributions . 38
2.4.3 Modeling of Temperature Fields 39
2.5 Milling Process Modeling and Control 41
2.5.1 Types of Milling Cutters . 41
2.5.2 Milling Types 43
2.5.3 Milling Parameters and Cutting Layer Parameters . 45
2.5.4 Milling Forces 49
2.5.5 The Milling System Dynamics 51
2.6 High-Speed Machining 56
2.6.1 Introduction to High-Speed Machining . 56
2.6.2 Advantages of High-Speed Machining . 58
2.6.3 Modeling of the Three-Dimensional Instantaneous
Milling Force 59
2.7 Control of Machining Process 63
References 67
3 Tool Wear and Modeling . 71
3.1 Types of Tool Wear . 71
3.1.1 Crater Wear 72
3.1.2 Flank Wear 72
3.1.3 Boundary Wear . 73
3.1.4 Tool Wear Criteria 74
3.2 The Formation of Tool Wear . 75
3.2.1 Mechanical Wear . 76
3.2.2 Adhesive Wear . 76
3.2.3 Diffusion Wear . 77
3.2.4 Chemical Wear . 78
3.2.5 Thermoelectric Wear 78
3.3 Tool Usability and Its Relationship with Cutting Parameters 79
3.3.1 Tool Life 79
3.3.2 Tool Life Equation 79
3.3.3 Tool Breakage 83
3.4 Modeling of Tool Wear 83
3.4.1 Abrasive Wear Rate Model . 84
3.4.2 Adhesive Wear Rate Model 85
3.4.3 Diffusion Wear Rate Model 86
3.4.4 Comprehensive Wear Rate Model . 87
3.4.5 Intelligent Tool Wear Model 88Contents xiii
3.5 Tool Wear Modeling in High-Speed Milling 89
3.5.1 Tool Flank Wear Conditions 89
3.5.2 Modeling of Tool Flank Wear . 90
3.5.3 Generalization of the Tool Wear Model 92
3.5.4 Analysis of Tool Wear Model . 95
References 100
4 Mathematical Foundations of Machining System Monitoring 103
4.1 Machining System Monitoring . 103
4.1.1 The Content of Machining System Monitoring 103
4.1.2 The System of Machining Process Monitoring 104
4.2 The Content of the Machining Process Monitoring System . 107
4.2.1 Signal Detection 107
4.2.2 Feature Extraction 107
4.2.3 State Recognition . 108
4.2.4 Decision-Making and Control 108
4.3 The Methods of Machining Process Monitoring . 109
4.3.1 Introduction 109
4.3.2 Stochastic Process Based Methods 110
4.4 Parameter Estimation Methods . 112
4.4.1 Least Square Estimation . 113
4.4.2 Yule-Walker Estimation . 114
4.4.3 Maximum Likelihood Estimate . 115
4.5 Time Series Analysis in Condition Monitoring 116
4.5.1 The Auto-Regression Model AR(N) . 116
4.5.2 The Auto Regression Moving Average Model
ARMA(n, m) 117
4.6 The Machining State Description . 119
4.6.1 Typical Anomaly State of the Machining Process 120
4.6.2 Process Model Based State Feature Extraction 121
4.7 Identification of Machining Process . 123
4.7.1 Overview of Process Modeling . 123
4.7.2 Model of Machining Process and Identification
Method 124
4.7.3 The Time Series Identification of the Machining
State 127
4.7.4 Identification of the Cutting Force . 129
4.7.5 Neural Network Identification of Machining
Process 130
4.8 The Common Measurement Methods and Characteristics 132
References 136xiv Contents
5 The Smart Machining System Monitoring from Machine
Learning View 139
5.1 The Condition Monitoring Methods . 139
5.1.1 Empirical Analysis 139
5.1.2 Statistical Method 140
5.1.3 Intelligent Method 143
5.2 Smart Machining System Monitoring (MSM) as a Machine
Learning Problem 144
5.2.1 Feature 145
5.2.2 State 145
5.2.3 Classifier 146
5.3 The MSM System Content . 146
5.3.1 Signal Preprocessing 146
5.3.2 Feature Extraction and Selection 148
5.3.3 State Classification 150
5.4 Feature Selection Method . 150
5.4.1 Effective Criteria for Monitoring Features 151
5.4.2 Optimal Monitoring Feature Group Selection . 154
5.4.3 The Bidirectional Search Algorithm for Feature
Selection 156
5.5 Machine Learning Method . 157
5.5.1 Bayesian Classifier 157
5.5.2 Fisher Linear Discriminant . 158
5.5.3 Principal Components Analysis . 159
5.5.4 Kernel Principal Components Analysis 159
5.5.5 Support Vector Machines 161
5.5.6 Artificial Neural Network (ANN) . 163
5.5.7 K-Nearest Neighbor (KNN) 164
5.5.8 Case Study: MSM with Self-Organizing Map
(SOM) 165
5.6 Deep Learning . 168
5.6.1 Introduction to Deep Learning 168
5.6.2 Sparse Autoencoder (AE) 170
5.6.3 Deep Belief Neural Network (DBN) . 174
5.6.4 Convolution Neural Network (CNN) . 178
5.6.5 Recurrent Neural Network (RNN) . 181
5.6.6 Challenges of Deep Learning Approaches
in MSM Process Monitoring . 187
References 188
6 Signal Processing for Machining Process Modeling
and Condition Monitoring . 191
6.1 Signal Processing in Condition Monitoring . 191
6.1.1 Overview of Condition Monitoring 191
6.1.2 Signal Processing Issues in Condition Monitoring . 192Contents xv
6.2 Signal Space, Linear System, and Fourier Transform 193
6.2.1 Signal Spaces and Inner Product 193
6.2.2 Fourier Transform 195
6.2.3 Linear System, Sampling Theorem,
and Convolution 195
6.3 Spectrum Analysis of Machining Signals 197
6.3.1 The Spectrum of Machining Signals . 197
6.3.2 Spectrum Characteristics of Stochastic Signals 199
6.4 Correlation Analysis 202
6.4.1 Autocorrelation Function 202
6.4.2 Cross-Correlation Function . 203
6.5 Common Signal Features in Time and Frequency Domain 204
6.5.1 Feature Parameters in the Time Domain 204
6.5.2 Feature Parameters in the Frequency Domain . 207
6.6 Wavelet Analysis . 209
6.6.1 Limitation of Fourier Methods 209
6.6.2 Continuous Wavelet Analysis (CWT) and Its
Time–Frequency Properties 211
6.6.3 Discrete Wavelet Transform and Its
Implementation . 214
6.6.4 Wavelet Basis Function 217
6.6.5 Wavelet Packets Decomposition 221
6.6.6 Some Remarks on Wavelet Transform . 222
6.7 Sparse Decomposition of Signals . 226
6.7.1 Compressive Sensing 226
6.7.2 Sparse Decomposition Over Pre-defined
Dictionaries 227
6.7.3 Greedy Algorithms 229
6.7.4 Dictionary Learning for Redundant Representation 232
References 233
7 Tool Condition Monitoring with Sparse Decomposition . 235
7.1 Introduction . 235
7.2 Sparse Coding for Denoising (Heavy Non-Gaussian Noise
Separation) 237
7.2.1 Introduction 237
7.2.2 Noise Properties in Micro-milling . 238
7.2.3 Sparse Representation in the Time–Frequency
Domain . 240
7.2.4 Sparse Representation as a Convex Optimization
Problem . 241
7.2.5 Case Studies . 243
7.3 Sparse Representation for Tool State Estimation 249
7.3.1 Sparse Coding of Wavelet Packet Decomposition
Coefficients 250xvi Contents
7.3.2 The Discriminant Dictionary Learning . 252
7.3.3 Fast Tool State Estimation Without Signal
Reconstruction . 254
7.3.4 Experimental Validation . 255
7.3.5 Results and Discussions . 257
References 264
8 Machine Vision Based Smart Machining System Monitoring 267
8.1 Machine Vision System for Machining Process Monitoring . 267
8.1.1 Introduction 267
8.1.2 The State-of-the-Art . 268
8.2 Digital Image Acquisition and Representation 271
8.2.1 Image Acquisition of the Monitored Objects 271
8.2.2 CCD Sensor . 272
8.2.3 CMOS Sensor 273
8.2.4 Representation of Digital Images 273
8.2.5 Digital Image Processing 275
8.3 Machine Vision System for Micro Milling Tool Condition
Monitoring 277
8.3.1 The Micro Milling Tool Condition Monitoring 277
8.3.2 Tool Wear Inspection System . 279
8.3.3 Tool Wear Inspection Method 282
8.3.4 Experimental Verification 288
8.3.5 Conclusions 292
References 293
9 Tool Wear Monitoring with Hidden Markov Models 297
9.1 Introduction . 297
9.2 HMM Based Methods 299
9.2.1 Hidden Markov Models 299
9.2.2 Three Problems of Hidden Markov Models . 300
9.3 Hidden Markov Models Based Tool Condition Monitoring . 301
9.3.1 HMM Description of Tool Wear Process
and Monitoring . 301
9.3.2 The Framework of HMMs for TCM . 303
9.3.3 Hidden Markov Model Selection: Continuous
Left–Right HMMs 303
9.3.4 Selection of the Number of Gaussian Mixture
Components . 306
9.3.5 On the Number of Hidden States in Each HMM . 307
9.3.6 Estimation of the HMM Parameters for Tool Wear
Classification 308
9.3.7 Tool State Estimation with HMMs 310
9.4 Experimental Verifications . 311
9.4.1 Experiment Setup . 311
9.4.2 HMM Training for TCM . 312Contents xvii
9.4.3 HMM for Tool Wear State Estimation 312
9.4.4 Moving Average for Tool Wear State Estimation
Smoothing . 314
9.4.5 On the Generalization of the HMM-Based
Algorithm for TCM . 315
9.5 Diagnosis and Prognosis of Tool Life with Hidden
Semi-Markov Model 317
9.5.1 Hidden Semi-Markov Model for Degradation
Process Modeling . 318
9.5.2 On-Line Health Monitoring via HSMM 320
9.6 Experimental Validation . 326
9.6.1 Case Study 326
9.6.2 Feature Extraction and Quantization . 327
9.6.3 Training of HSMM for Tool Wear Monitoring 328
9.6.4 Diagnosis and Prognosis Results 331
References 335
10 Sensor Fusion in Machining System Monitoring 339
10.1 Multi-sensor Information Fusion Principle . 339
10.2 Multi-sensor Information Fusion with Neural Networks 340
10.3 Sensor Fusion with Deep Learning 344
10.3.1 Problem Formulation 346
10.3.2 The Unit of Pyramid LSTM Auto-encoder 347
10.3.3 The Structure of the Pyramid LSTM Auto-encoder 350
10.3.4 The Training Method 351
10.3.5 Computational Efficiency 352
10.3.6 Experimental Validation . 353
10.3.7 Conclusion 359
References 359
11 Big Data Oriented Smart Tool Condition Monitoring System 361
11.1 The Big Data Issues in Manufacturing . 361
11.2 The Big Data Analytics in Smart Machining System . 362
11.2.1 The Big Data Challenges and Motivation . 362
11.2.2 Related Works 363
11.3 The Framework of Big Data Oriented Smart Machining
Monitoring System . 365
11.3.1 The Monitoring System Architecture 365
11.3.2 The Big Data-Oriented Formulation of TCM 366
11.4 The Functional Modules and Case Study . 366
11.4.1 Sparse Coding Based Data Pre-processing 367
11.4.2 In-process Workpiece Integrity Monitoring . 369
11.4.3 Heterogeneous Data Fusion and Deep Learning . 370
11.4.4 Intelligent Tool Monitoring and Wear
Compensation 372
11.5 Case Study 375xviii Contents
11.6 Summary . 379
References 379
12 The Cyber-Physical Production System of Smart Machining
System . 383
12.1 Introduction . 383
12.2 The Cyber-Physical System in Manufacturing 383
12.2.1 The Definition 383
12.2.2 The CPS Features . 384
12.3 The CPS of Machine Tool and Machining Process 386
12.3.1 The State-of-the-Art . 386
12.3.2 The CPS of Machine Tool 388
12.3.3 The CPS of Machining Process . 389
12.4 A CPPS Framework of Smart Machining Monitoring
System . 393
12.4.1 Induction 393
12.4.2 The Smart CNC Machining Monitoring CPPS
Structure 395
12.4.3 Case Studies . 398
12.5 Summary . 404
References .
References

  1. Kagermann H, Wahlster W, Helbig J (2012) Securing the future of German manufacturing
    industry recommendations for implementing the strategic initiative INDUSTRIE 4.0. Federal
    Ministry of education and research Final report of the Industrial 4.0 Working Group, Germany
  2. Lee EA (2006) Cyber-physical systems—are computing foundations adequate? Position paper
    for NSF workshop on cyber physical systems: research motivation, techniques and roadmap
  3. Rajkumar R, Lee I (2010) Cyber-physical systems: the next computing revolution. Proceedings
    of the design automation conference. pp 731–736
  4. Harrison R, Vera D, Ahmad B (2016) Engineering methods and tools for cyber–physical
    automation systems. IEEE Proc 104(5):973–985
  5. Sztipanovits J, Karsai G, et al (2012) Toward a science of cyber–physical system integration.
    Proc IEEE 100(1)
  6. Leitao P, Colombo AW, Karnouskos S (2016) Industrial automation based on cyber-physical
    systems technologies: prototype implementations and challenges. Comput Ind 81:11–25
  7. Groover MP (2015) Automation, production systems, and computer-integrated manufacturing,
    4th edn. Pearson
  8. Liu C, Xu X (2017) Cyber-physical machine tool—the era of machine tool 4.0. Procedia CIRP
    63:70–75
  9. Ghimire S, Luis-Ferreira F, Nodehi T, et al (2017) IoT based situational awareness framework
    for real-time project management. Int J Comput Integr Manuf 30(1):74–83
  10. Zhong RY, Wang L, Xu X (2017) An IoT-enabled real-time machine status monitoring approach
    for cloud manufacturing. Procedia CIRP 63:709–714
  11. Zuo Y, Tao F, Nee AYC (2017) An internet of things and cloud-based approach for energy
    consumption evaluation and analysis for a product. Int J Comput Integr Manuf. 1–12
  12. Cai Y, Starly B, Cohen P, et al (2017) Sensor data and information fusion to construct digitaltwins virtual machine tools for cyber-physical manufacturing. 10:1031–1042
  13. Zheng M, Ming X (2017) Construction of cyber-physical system–integrated smart manufacturing workshops: a case study in automobile industry. Adv Mech Eng 9(10):168781401773324
  14. Zhang J, Deng C, et al (2021) Development of an edge computing-based cyber-physical
    machine tool. Robot Comput Integr Manuf 67:102042
  15. Luo W, Hu T, Ye Y, Zhang C, Wei Y (2020) A hybrid predictive maintenance approach for
    CNC machine tool driven by digital twin. Robot Comput Integr Manuf 65:101974
  16. Xie Y, Lian K (2021) Digital twin for cutting tool: modeling, application and service strategy.
    J Manuf Syst 58(B):305–312
  17. Morgan J, O’Donnell GE (2015) Cyber physical process monitoring systems. J Int Manuf
    26(6):1–12
  18. Caggiano A, Segreto T, Teti R (2016) Cloud manufacturing framework for smart monitoring
    of machining. Procedia CIRP 55:248–253
  19. Herwan J, Kano S, et al (2018) Cyber-physical system architecture for machining production
    line. In: IEEE industrial cyber-physical systems (ICPS). St. Petersburg, Russia
  20. Zhu KP, Zhang Y (2018) A cyber-physical production system framework of smart CNC
    machining monitoring system. IEEE/ASME Trans Mechatron 23(6):2579–2586406 12 The Cyber-Physical Production System of Smart Machining System
  21. Teti R, Jemielniak K, O’Donnel G, Dornfeld D (2010) Advanced monitoring of machining
    operations. CIRP Ann Manuf Technol 59(2):717–739
  22. Deshayes L, Welsch L, Donmez A, Ivester R, Gilsinn D, Rhorer R, Whitenton E, Potra F (2005)
    Smart machining systems: issues and research trends. The 12th CIRP life cycle engineering
    seminar, Grenoble, France, pp 3–5
  23. Gao R, Wang L, Teti R, Dornfeld D, Kumara S, Mori M, Helu M (2015) Cloud-enabled
    prognosis for manufacturing. CIRP Ann Manuf Technol 64(2):749–772
  24. Altintas Y, Kersting P, Biermann D, Budak E, Denkena B, Lazoglu I (2014) Virtual process
    systems for part machining operations. CIRP Ann Manuf Technol 63(2):585–605
  25. Lee J, Lapira E, Bagheri B, Kao HA (2012) Recent advances and trends in predictive
    manufacturing systems in big data environment. Manuf Lett 1(1):38–41
  26. Monostori L, Kadar B, Bauernhansl T, Kondoh S, Kumara S, Reinhart G, Sauer O, Schuh G,
    Sihn W, Ueda K (2016) Cyber-physical systems in manufacturing. CIRP Ann Manuf Technol
    65(2):621–641
  27. Foundations for Innovation in Cyber-Physical Systems (2014) National Institute of Standards
    and Technology (NIST), Gaithersburg
  28. Lv C, Liu Y, Hu X, et al (2018) Simultaneous observation of hybrid states for cyber-physical
    systems: a case study of electric vehicle powertrain. IEEE Trans Cybern 48(8):2357–2367
  29. Lv C, Xing Y, Zhang J, Na X, et al (2018) Levenberg-Marquardt backpropagation training of
    multilayer neural networks for state estimation of a safety critical cyber-physical system. IEEE
    Trans Industr Inform 14(8):3436–3446
  30. Mourtzis D, Vlachou E, Milas N, Xanthopoulos N (2016) A cloud-based approach for maintenance of machine tools and equipment based on shop-floor monitoring. Procedia CIRP
    41:655–660
  31. Tapoglou N, Mehnen J, Vlachou A, Doukas M, Milas N, Mourtzis D (2015) Cloud-based
    platform for optimal machining parameter selection based on function blocks and real-time
    monitoring. J Manuf Sci Eng 137(4):040909
  32. Li X, Djordjevich A, Venuvinod PK (2000) Current-sensor-based feed cutting force intelligent
    estimation and tool wear condition monitoring. IEEE Trans Ind Electron 47(3):697–702
  33. Hung CW, Lu MC (2012) Model development for tool wear effect on AE signal generation in
    micro-milling. Int J Adv Manuf Technol 66(9–12):1845–1858
  34. Szydłowski M, Powałka B, Matuszak M, et al (2016) Machine vision micro-milling tool wear
    inspection by image reconstruction and light reflectance. Prec Eng 44:236–244
  35. Zhu KP, Yu XL (2017) The monitoring of micro milling tool wear conditions by wear area
    estimation. Mech Syst Signal Process 93:80–91
  36. Kuljanic E, Sortino M, Totis G (2008) Multisensor approaches for chatter detection in milling.
    J Sound Vib 312(4–5):672–693
  37. Wang W, Jianu OA (2010) A smart sensing unit for vibration measurement and monitoring.
    IEEE/ASME Trans Mechatron 15(1):70–78
  38. Rizal M, Ghani JA, Nuawi MZ, Haron CHC (2015) Development and testing of an integrated
    rotating dynamometer on tool holder for milling process. Mech Syst Signal Process 52–53:559–
    576
  39. Mahajan A, Wang K, Ray PK (2001) Multisensor integration and fusion model that uses a
    fuzzy inference system. IEEE/ASME Trans Mech 6(2):188–196
  40. Malekian M, Park SS, Jun MBG (2009) Tool wear monitoring of micro-milling operations. J
    Mat Process Technol 209(10):4903–4914
  41. Wang J, Xie J, Zhao R, Mao K, Zhang L (2016) A new probabilistic kernel factor analysis for
    multisensory data fusion: application to tool condition monitoring. IEEE Trans Instrum Meas
    65(11):2527–2537
  42. Ompusunggu AP, Papy JM, Vandenplas S (2015) Kalman-filtering-based prognostics for
    automatic transmission clutches. IEEE/ASME Trans Mech 21(1):419–430
  43. Zhu KP, Liu T (2018) Online tool wear monitoring via hidden Semi-Markov model with
    dependent durations. IEEE Trans Ind Inform 14(1):69–78References 407
  44. Geramifard O, Xu JX, Zhou JH, Li X (2012) Multimodal hidden Markov model-based approach
    for tool wear monitoring. IEEE Trans Ind Electron 61(6):2900–2911
  45. Xia M, Li T, Xu L, Liu L, Silva CWD (2018) Fault diagnosis for rotating machinery using
    multiple sensors and convolutional neural networks. IEEE/ASME Trans Mech 23(1):101–110
  46. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117
  47. Wang P, Yan AR, Gao R (2017) Visualization and deep recognition for system fault
    classification. J Manuf Syst 44:310–316
  48. Droniou A, Ivaldi S, Sigaud O (2015) Deep unsupervised network for multimodal perception,
    representation and classification. Robot Auton Syst 71:83–98
  49. Sun W, Shao S, Zhao R, Yan R, Zhang X, Chen X (2016) A sparse auto-encoder-based deep
    network approach for induction motor faults classification. Measurement 89:171–178
  50. Monostori L (2014) Cyber-physical production systems: roots, expectations and R&D
    challenges. Procedia CIRP 17:9–13
  51. Lee J, Bagheri B, Kao HA (2015) A cyber-physical systems architecture for industry 4.0-based
    manufacturing systems. Manuf Lett 3:18–23
  52. Zhu KP, Zhang Y (2017) Modeling of the instantaneous milling force per tooth with tool run-out
    effect in high speed ball-end milling. Int J Mach Tools Manuf 118–119:37–48
  53. Morgan J, O’Donnell GE (2017) Multi-sensor process analysis and performance characterization in CNC turning-a cyber physical system approach. Int J Adv Manuf Technol
    92(1–4):855–868

كلمة سر فك الضغط : books-world.net
The Unzip Password : books-world.net

تحميل

يجب عليك التسجيل في الموقع لكي تتمكن من التحميل
تسجيل | تسجيل الدخول

التعليقات

اترك تعليقاً