Intelligent Production and Manufacturing Optimisation―The Bees Algorithm Approach

Description

This book is the first work dedicated to the Bees Algorithm. Following a gentle introduction to the main ideas underpinning the algorithm, the book presents recent results and developments relating to the algorithm and its application to optimisation problems in production and manufacturing.   With the advent of the Fourth Industrial Revolution, production and manufacturing processes and systems have become more complex. To obtain the best performance from them requires efficient and effective optimisation techniques that do not depend on the availability of process or system models. Such models are usually either not obtainable or mathematically intractable due to the high degrees of nonlinearities and uncertainties in the processes and systems to be represented. The Bees Algorithm is a powerful swarm-based intelligent optimisation metaheuristic inspired by the foraging behaviour of honeybees. The algorithm is conceptually elegant and extremely easy to apply. All it needs to solve an optimisation problem is a means to evaluate the quality of potential solutions.   This book demonstrates the simplicity, effectiveness and versatility of the algorithm and encourages its further adoption by engineers and researchers across the world to realise smart and sustainable manufacturing and production in the age of Industry 4.0 and beyond.   Preface Acknowledgements Contents Introduction The Bees Algorithm—A Gentle Introduction 1 Introduction 2 Parameter Optimisation 2.1 Discrete Optimisation: The Travelling Salesman Problem 2.2 Heuristics 2.3 Continuous Optimisation: Function Maximisation 3 Bee Inspired! Intelligent Optimisation with the Bees Algorithm 3.1 Honey Bees Foraging Behaviour 3.2 The Bees Algorithm 3.3 The Standard Bees Algorithm 3.4 The Bees Algorithm for Discrete Optimisation Problems 4 Variants of the Bees Algorithm 5 Discussion 6 Conclusions References Manufacturing Process Optimisation Minimising Printed Circuit Board Assembly Time Using the Bees Algorithm with TRIZ-Inspired Operators 1 Introduction 2 Bees Algorithm 3 Theory of Inventive Problem Solving 4 MBTD PCB Assembly 5 Application of TRIZ to Operator Generation 5.1 Dynamisation Operator 5.2 Segmentation Operator 5.3 Local Quality Operator 6 The Bees Algorithm with TRIZ-Inspired Operators 7 PCB Assembly Involving 50 Components (10 Different Types of Components)—A Case Study 8 Discussions 9 Conclusions References The application of the Bees Algorithm in a Digital Twin for Optimising the Wire Electrical Discharge Machining (WEDM) Process Parameters 1 Introduction 2 Literature Review 3 Wire Electrical Discharge Machining (WEDM) 4 Virtual Machine Creation 4.1 Program Architecture 4.2 Bees Algorithm Optimisation Testing and Results 5 Discussion of Results 6 Conclusions and Future Work References A Case Study with the BEE-Miner Algorithm: Defects on the Production Line 1 Introduction 2 Cost-Sensitive Classifiers 2.1 BEE-Miner Algorithm 2.2 MEPAR-Miner Algorithm 3 Experimental Study 4 Conclusion References An Application of the Bees Algorithm to Pulsating Hydroforming 1 Introduction 2 Methodology 2.1 Design of the Experimental Data Set 2.2 Obtaining Mathematical Expression for the Bulge Height via Experimental Data 2.3 Validation of Mathematical Modelling 2.4 Applying the Bees Algorithm to the Hydroforming Process 3 Results and Discussion 4 Conclusion References Production Equipment Optimisation Shape Recognition for Industrial Robot Manipulation with the Bees Algorithm 1 Introduction 2 Literature Review 3 Primitive Fitting Methods 3.1 Representation Scheme 3.2 Fitness Function 3.3 Local Search Operator 4 Experimental Set Up 4.1 Datasets 4.2 Error Evaluation Function 4.3 Parameterisation of Algorithms 5 Results 6 Conclusions and Further Work References Bees Algorithm Models for the Identification and Measurement of Tool Wear 1 Introduction 2 Bees Algorithm 3 Turning Trials 3.1 Tool Wear Measurements 4 Bees Algorithm for Tool Wear Detection 5 Results 6 Discussion and Conclusions References Global Optimisation for Point Cloud Registration with the Bees Algorithm 1 Introduction 2 Related Work 3 Problem Formulation 4 Methodology 4.1 Encoding of the Candidate Solutions 4.2 Fitness Function for 3D Registration Evaluation 4.3 SVD Operation for 3D Point Cloud Registration 4.4 Iterative Closest Point (ICP) 4.5 The Bees Algorithm for 3D Registration 5 Experiments and Discussion 5.1 Dataset and Parameter Settings 5.2 Consistency 5.3 Precision 5.4 Robustness to Noise 6 Conclusion References Automatic PID Tuning Toolkit Using the Multi-Objective Bees Algorithm 1 Introduction 2 PID Control and Tuning Methods 3 Bees Algorithm and Multi-Objective Optimisation 4 Automatic PID Tuner 5 Discussion and Conclusion References The Effect of Harmony Memory Integration into the Bees Algorithm 1 Introduction 2 The Design Problem 3 The Bees Algorithm and Integration 4 Results and Discussion 5 Conclusion References Memory-Based Bees Algorithm with Lévy Flights for Multilevel Image Thresholding 1 Introduction 2 Lévy Flights and Honey Bees 2.1 Lévy Flights with MBA 2.2 Initialisation Step-Based Lévy Flights 2.3 Bees-Movement-Based Lévy Flights 3 Otsu’s Image Thresholding and PSNR 4 Experimental Results 4.1 Benchmark Test Functions 4.2 MBA and LMBA with PSNR for Multilevel Image Thresholding 5 Results Analysis for Standard Images 6 Conclusion References Α New Method to Generate the Initial Population of the Bees Algorithm for Robot Path Planning in a Static Environment 1 Introduction 2 The Proposed Method 2.1 Configuration Space 2.2 Initialise the Population of the Bees Algorithm 2.3 The Fitness Function 2.4 Local Search 2.5 Global Search 2.6 Neighbourhood Shrinking 3 Results 4 Comparison 5 Conclusion References Production Plan Optimisation Method for the Production Planning and Scheduling of a Flexible Manufacturing Plant Based on the Bees Algorithm 1 Introduction 1.1 Background 1.2 Literature Review 2 Mathematical Modelling 2.1 Objective Function 2.2 Boundary Conditions 2.3 Encoding and Decoding 3 The Bees Algorithm 3.1 BA with Site Abandonment Technique 3.2 Local Search 4 Simulation Results 4.1 Results of BA 4.2 Results of the Improved Bees Algorithm 4.3 Comparison of Results 5 Conclusions References Application of the Dual-population Bees Algorithm in a Parallel Machine Scheduling Problem with a Time Window 1 Introduction 2 Model 2.1 Symbols and Variables 2.2 Problem Description 2.3 Mathematical Model 3 Dual-population Bees Algorithm 3.1 Overall Flow of the Algorithm 3.2 Coding 3.3 Scout Bee Stage 3.4 Forager Bee Stage 3.5 Elite Bee Stage 3.6 Population Dynamic Adjustment 3.7 Fitness Function 4 Experiment 5 Conclusion References A Parallel Multi-indicator-Assisted Dynamic Bees Algorithm for Cloud-Edge Collaborative Manufacturing Task Scheduling 1 Introduction 2 Modeling and Problem Formulation 3 Algorithm 3.1 Framework 3.2 Individual Encoding 3.3 Pre-allocation Mechanism 3.4 Sorting Strategy 3.5 Improved Bees Algorithm 3.6 Merging and Adjustment Strategy 4 Experiments 4.1 Comparison of Sorting Strategies 4.2 Comparison of Adjustment Strategies 4.3 Algorithm Performance Comparison 5 Conclusion References Logistics and Supply Chain Optimisation Bees Traplining Metaphors for the Vehicle Routing Problem Using a Decomposition Approach 1 Introduction 2 Bees Algorithm 2.1 Basic Version 2.2 Traplining Metaphor I: Parameter Reduction (Two-Parameter BA) 2.3 Traplining Metaphor II: Intensifier (Bees Routing Optimiser) 3 Vehicle Routing Problem 4 Methodology 4.1 Clustering Procedure 4.2 Routing Procedure 5 Experiments, Results and Discussion 6 Conclusion Appendix A: The Complete Routing Plan Appendix B: Details of the Clustering Method Appendix C: Acronyms and Symbols References Supply Chain Design and Multi-objective Optimisation with the Bees Algorithm 1 Introduction 2 Supply Chain Network Design Problem 2.1 Mathematical Model 3 The Bees Algorithm Approach 3.1 Notes on the Foraging Behaviour of Honeybees 3.2 Notes on the Bees Algorithm 4 Bees Algorithm Approach for Solving the Multi-objective Supply Chain Optimisation Problem 4.1 Numerical Example 5 Conclusions References Remanufacturing Collaborative Optimisation of Robotic Disassembly Planning Problems using the Bees Algorithm 1 Introduction 2 Literature Review 3 The Collaborative Optimization Problem 3.1 Assumption, Definition and Workflow 3.2 Feasible Disassembly Sequence Generation 3.3 Optimization Objectives and the Weights 4 The Improved Discrete Bees Algorithm 4.1 Representation of Bees 4.2 Variable Neighborhood Search 4.3 Global Search 5 Results and Simulations 5.1 Case Studies 5.2 Calculating Weights of Indicators 5.3 Performance Analysis 5.4 Simulations Based on RoboDK 6 Conclusion Appendix References Optimisation of Robotic Disassembly Sequence Plans for Sustainability Using the Multi-objective Bees Algorithm 1 Introduction 2 Literature Review 3 Model and Methodology 4 Experiments 4.1 Robotic Cell 4.2 Key Input Data and Calculation Assumptions 5 Results and Discussion 6 Conclusion Appendix References Task Optimisation for a Modern Cloud Remanufacturing System Using the Bees Algorithm 1 Introduction 2 The Bees Algorithm in Manufacturing and Remanufacturing Contexts 3 The Cloud Remanufacturing Model 3.1 Completion Time Evaluation in the Cloud Remanufacturing Model 4 The Makespan Problem 5 Case Study 5.1 Experiments Settings 5.2 Results Analysis 6 Conclusion Appendix References Prediction of the Remaining Useful Life of Engines for Remanufacturing Using a Semi-supervised Deep Learning Model Trained by the Bees Algorithm 1 Introduction 2 Related Work 3 Proposed Semi-supervised Deep Learning Model for RUL Estimation of the NASA Turbofan Engine Dataset 3.1 Long Short-Term Memory (LSTM) Networks 3.2 A Modified Ternary Bees Algorithm for Training a Deep Learning Model 4 Experiments 4.1 Experimental Setup and Parameter Tuning 4.2 Results 5 Conclusion References Index