This volume serves as the technical analysis to a report concerning the potential for artificial intelligence systems to assist in Air Force command and control (C2). The authors present their analysis of the problem characteristics and solution capabilities described in Volume 1. They provide details about the expert panel used to gather data and three technical case studies that demonstrate a wide range of solutions to various C2 problems.

This volume serves as the technical analysis to a report concerning the potential for artificial intelligence (AI) systems to assist in Air Force command and control (C2) from a technical perspective. The authors detail the taxonomy of ten C2 problem characteristics. They present the results of a structured interview protocol that enabled scoring of problem characteristics for C2 processes with subject-matter experts (SMEs). Using the problem taxonomy and the structured interview protocol, they analyzed ten games and ten C2 processes. To demonstrate the problem taxonomy and the structured interview protocol for a C2 problem, they then applied them to sensor management as performed by an air battle manager. The authors then turn to eight AI system solution capabilities. As for the C2 problem characteristics, they created a structured protocol to enable valid and reliable scoring of solution capabilities for a given AI system. Using the solution taxonomy and the structured interview protocol, they analyzed ten AI systems. The authors present additional details about the design, implementation, and results of the expert panel that was used to determine which of the eight solution capabilities are needed to address each of the ten problem characteristics. Finally, they present three technical case studies that demonstrate a wide range of computational, AI, and human solutions to various C2 problems.

This volume contains the 5 invited papers and 72 selected papers that were presented at the Fifth International Conference on Industrial and Engineering Applications of Artificial Intelligence. This is the first IEA/AIE conference to take place outside the USA: more than 120 papers were received from 23 countries, clearly indicating the international character of the conference series. Each paper was reviewed by at least three referees. The papers are grouped into parts on: CAM, reasoning and modelling, pattern recognition, software engineering and AI/ES, CAD, vision, verification and validation, neural networks, machine learning, fuzzy logic and control, robotics, design and architecture, configuration, finance, knowledge-based systems, knowledge representation, knowledge acquisition and language processing, reasoning and decision support, intelligent interfaces/DB and tutoring, fault diagnosis, planning and scheduling, and data/sensor fusion.

This report concerns the potential for artificial intelligence (AI) systems to assist in Air Force command and control (C2) from a technical perspective. The authors present an analytical framework for assessing the suitability of a given AI system for a given C2 problem. The purpose of the framework is to identify AI systems that address the distinct needs of different C2 problems and to identify the technical gaps that remain. Although the authors focus on C2, the analytical framework applies to other warfighting functions and services as well. The goal of C2 is to enable what is operationally possible by planning, synchronizing, and integrating forces in time and purpose. The authors first present a taxonomy of problem characteristics and apply them to numerous games and C2 processes. Recent commercial applications of AI systems underscore that AI offers real-world value and can function successfully as components of larger human-machine teams. The authors outline a taxonomy of solution capabilities and apply them to numerous AI systems. While primarily focusing on determining alignment between AI systems and C2 processes, the report's analysis of C2 processes is also informative with respect to pervasive technological capabilities that will be required of Department of Defense (DoD) AI systems. Finally, the authors develop metrics-based on measures of performance, effectiveness, and suitability-that can be used to evaluate AI systems, once implemented, and to demonstrate and socialize their utility.

Integrated Process Modeling, Advanced Control and Data Analytics for Optimizing Polyolefin Manufacturing Detailed resource on the “Why,” “What,” and “How” of integrated process modeling, advanced control and data analytics explained via hands-on examples and workshops for optimizing polyolefin manufacturing. Integrated Process Modeling, Advanced Control and Data Analytics for Optimizing Polyolefin Manufacturing discusses, as well as demonstrates, the optimization of polyolefin production by covering topics from polymer process modeling and advanced process control to data analytics and machine learning, and sustainable design and industrial practice. The text also covers practical problems, handling of real data streams, developing the right level of detail, and tuning models to the available data, among other topics, to allow for easy translation of concepts into practice. Written by two highly qualified authors, Integrated Process Modeling, Advanced Control and Data Analytics for Optimizing Polyolefin Manufacturing includes information on: Segment-based modeling of polymer processes; selection of thermodynamic methods; estimation of physical properties for polymer process modeling Reactor modeling, convergence tips and data-fit tool; free radical polymerization (LDPE, EVA and PS), Ziegler-Natta polymerization (HDPE, PP, LLPDE, and EPDM) and ionic polymerization (SBS rubber) Improved polymer process operability and control through steady-state and dynamic simulation models Model-predictive control of polyolefin processes and applications of multivariate statistics and machine learning to optimizing polyolefin manufacturing Integrated Process Modeling, Advanced Control and Data Analytics for Optimizing Polyolefin Manufacturing enables readers to make full use of advanced computer models and latest data analytics and machine learning tools for optimizing polyolefin manufacturing, making it an essential resource for undergraduate and graduate students, researchers, and new and experienced engineers involved in the polyolefin industry.

This report documents and presents the results of a study to determine the feasibility of applying Artificial Intelligence (AI) techniques to the diagnosis of transit railcars. The AI techniques investigated were expert systems, case-based reasoning, model-based reasoning, artificial neural networks, computer vision, fuzzy logic, and a procedural knowledge-based system. Site surveys were conducted at transit railcar maintenance facilities and at railcar subsystem suppliers. The site surveys gathered information about current and future diagnostic and maintenance practices, possible barriers to implementing advanced AI technology, and maintenance cost data. An economic analysis was performed to provide an estimate of cost savings expected by reducing the diagnostic effort.