Chapter 6 Data-driven techniques for optimal and sustainable process integration of chemical and manufacturing systems
-
Daniel Rangel-Martínez
Abstract
One of the major challenges in the field of Process Systems Engineering (PSE) is the development of an integral approach to perform the optimization in chemical and manufacturing plants. This approach is complex as it consists of the simultaneous optimization of multiple hierarchical tasks that occur at different temporal and spatial scales in chemical plants. Challenges include the disparity in timescales among the different tasks, different operational, logical and tactical constraints, different objectives or goals, and the curse of dimensionality. To handle these situations, the continuously growing field of artificial intelligence (AI) has developed tools that can be used to reduce or overcome the complexity that these challenges pose to the integration. The application of AI techniques is largely supported by the growing volume of data that can be used for building data-driven models. In this work, a review of the literature in PSE that makes use of data-driven techniques to perform the optimal process integration in chemical and manufacturing plants is presented. The tasks involved in the optimal process integration discussed in this work include integration of process design and control, planning and scheduling, scheduling and control and planning, scheduling and control. Key insights combined with an outlook are presented and aim to provide the reader with a perspective of the current state of the art in this field.
Abstract
One of the major challenges in the field of Process Systems Engineering (PSE) is the development of an integral approach to perform the optimization in chemical and manufacturing plants. This approach is complex as it consists of the simultaneous optimization of multiple hierarchical tasks that occur at different temporal and spatial scales in chemical plants. Challenges include the disparity in timescales among the different tasks, different operational, logical and tactical constraints, different objectives or goals, and the curse of dimensionality. To handle these situations, the continuously growing field of artificial intelligence (AI) has developed tools that can be used to reduce or overcome the complexity that these challenges pose to the integration. The application of AI techniques is largely supported by the growing volume of data that can be used for building data-driven models. In this work, a review of the literature in PSE that makes use of data-driven techniques to perform the optimal process integration in chemical and manufacturing plants is presented. The tasks involved in the optimal process integration discussed in this work include integration of process design and control, planning and scheduling, scheduling and control and planning, scheduling and control. Key insights combined with an outlook are presented and aim to provide the reader with a perspective of the current state of the art in this field.
Chapters in this book
- Frontmatter I
- Contents V
- List of contributing authors VII
- Chapter 1 Optimization and its importance for chemical engineers: challenges, opportunities, and innovations 1
- Chapter 2 Deterministic optimization of distillation processes 25
- Chapter 3 Optimal design of process energy systems integrating sustainable considerations 79
- Chapter 4 Metaheuristics for the optimization of chemical processes 113
- Chapter 5 Surrogate-based optimization techniques for process systems engineering 159
- Chapter 6 Data-driven techniques for optimal and sustainable process integration of chemical and manufacturing systems 215
- Chapter 7 Applications of Bayesian optimization in chemical engineering 255
- Chapter 8 Sensitivity assessment of multi-criteria decision-making methods in chemical engineering optimization applications 283
- Chapter 9 Hybrid optimization methodologies for the design of chemical processes 305
- Chapter 10 Optimization under uncertainty in process systems engineering 343
- Chapter 11 Optimal control of batch processes in the continuous time domain 379
- Chapter 12 Supply chain optimization for chemical and biochemical processes 401
- Chapter 13 Future insights for optimization in chemical engineering 425
- Index 445
Chapters in this book
- Frontmatter I
- Contents V
- List of contributing authors VII
- Chapter 1 Optimization and its importance for chemical engineers: challenges, opportunities, and innovations 1
- Chapter 2 Deterministic optimization of distillation processes 25
- Chapter 3 Optimal design of process energy systems integrating sustainable considerations 79
- Chapter 4 Metaheuristics for the optimization of chemical processes 113
- Chapter 5 Surrogate-based optimization techniques for process systems engineering 159
- Chapter 6 Data-driven techniques for optimal and sustainable process integration of chemical and manufacturing systems 215
- Chapter 7 Applications of Bayesian optimization in chemical engineering 255
- Chapter 8 Sensitivity assessment of multi-criteria decision-making methods in chemical engineering optimization applications 283
- Chapter 9 Hybrid optimization methodologies for the design of chemical processes 305
- Chapter 10 Optimization under uncertainty in process systems engineering 343
- Chapter 11 Optimal control of batch processes in the continuous time domain 379
- Chapter 12 Supply chain optimization for chemical and biochemical processes 401
- Chapter 13 Future insights for optimization in chemical engineering 425
- Index 445
