Hjem

Preface ix About the Author xi Acknowledgments xiii 1 Survey of Challenges in Chemistry and Materials Science Research 1
1.1 Introduction 1
1.2 Energy Form 2
1.2.1 Steam Power 2
1.2.2 Electricity Power 4
1.2.3 Other Energy Forms 8
1.3 Data 11 References 19 2 Robots Technology Development in Modern Scientific Research 21
2.1 Introduction 21
2.2 Early Development of Laboratory Automation (Before 2000) 22
2.2.1 Early Automation Technologies 22
2.2.2 Laying the Foundation for AI and Robotics 29
2.3 Preliminary Integration and Development of Laboratory Automation (2000-2019) 31
2.3.1 Automation Technologies (2000-2010) 31
2.3.2 Various Forms of Exploration Based on Established Foundations 41
2.4 Latest Developments and Current Trends (2020-2023) 42
2.4.1 Automation Technologies in Five Years 42
2.4.2 Mature Industrialization as well as In-depth Exploration 50
2.5 Outlook on Future Development 52
2.6 Conclusion 54 References 55 3 AI Algorithm for Chemical and Bio-material Design 57
3.1 Introduction 57
3.2 Molecular Representation and Encoding 58
3.2.1 Linear Notations for Molecules 58
3.2.2 Graph Representations for Molecules 63
3.3 The Formulation of Accessible and Searchable Data 66
3.3.1 Traditional Way for Molecular Structure-Property Relationship Determination: The Kohn-Sham Equation 66
3.3.2 Dataset Preprocessing 68
3.3.3 Current Existing Dataset 69
3.4 AI for Molecular Structure-Property Relationship 71
3.4.1 The Deep Learning Technology 72
3.4.2 AI Solving the Kohn-Sham Equation 75
3.5 AI for Chemical and Bio-material Design 78
3.5.1 Design Workflows 78
3.5.2 Example of Designed Chemical and Bio-materials 79 References 81 4 Autonomous Laboratory Empowered by AI and Robotics 85
4.1 Evolution of Laboratory 85
4.2 Core Technologies in Autonomous Laboratories 85
4.2.1 Autonomous Laboratory Components 85
4.2.2 Reinforcement Learning 89
4.3 Example Autonomous Laboratory Solution 90
4.3.1 Automatic Device only Solution 90
4.3.2 Solution that Including Design and React 91
4.3.3 Solution in Reaction Optimization 92
4.3.4 Solutions Contain Full Phases 94
4.4 Advanced Autonomous Laboratory Solutions 98
4.4.1 Advanced Experimental Data Analysis Methods 98
4.4.2 Design and Analysis in the Large Model Era 104
4.4.3 Experiment Visualization 106
4.5 Future Prospects and Trends 108 References 110 5 Large Language Models for the Autonomous Material Research 113
5.1 Review of Large Language Models Development and Applications 113
5.2 Fundamentals of LLM for Material Research: Database and Knowledge Base Construction 121
5.3 Evaluation: Spider Matrix 124
5.4 Ideation: AI Supervisor and ScholarNet 130
5.5 Results and Discussion 134
5.6 Conclusion 136 References 136 6 Toward a Blockchain-Powered Anti-Counterfeiting Experimental Data System in an Autonomous Laboratory 139
6.1 Blockchain Technology 139
6.2 Laboratory Chemical Management and Safety 143
6.3 The Problem of Data Integrity and Counterfeiting in Scientific Research 145
6.4 Blockchain in the Autonomous Laboratory 150
6.5 Symbolic Representation of Experiments 155
6.6 Challenges and Limitations 157
6.6.1 Standard Compilation for Experiment Methods 157
6.6.2 High Cost for PoW and PoS 158
6.6.2.1 Data Storage Safety 158
6.7 Conclusion 159 References 160 7 The Future Integrated Computational and Experimental Research in Metaverse 163
7.1 Introduction of Metaverse 163
7.1.1 Industry
5.0 Protocol 163
7.1.2 Current Development of Metaverse 164
7.1.3 Human-in-Loop Paradigm 165
7.2 Research Paradigm in Metaverse 165
7.3 Autonomous High-Throughput Experiments 166
7.3.1 Theory Driven by AI 168
7.3.2 HIL Implementation 169
7.3.3 AI Prediction 171
7.4 H2O Phase Research in Metaverse 172
7.5 Aqueous System Research in Metaverse 176
7.6 Challenges and Future Directions 182 References 182 Index 187