Artificial intelligence for securing industrial-based cyber–physical systems

Abstract

Objective:The combination of artificial intelligence and cyber–physical​ systems (CPSs) in buildings has many advantages. Therefore, CPSs and artificial intelligence are studied based on previous research to promote their use in the construction industry. Methods:The design scheme of a CPS-based indoor environment measurement and control system for intelligent buildings is based on four modules: detection, control, execution, and communication. An agent is utilized as the smallest control unit, and the multi-agent system (MAS) simulates the connections between human neurons to achieve autonomous and flexible access to information. Multi-agents are utilized to imitate the connections between human neurons. The physical world of the physics-based information fusion system is constructed. The basic concept of granular computing and the principle of granular formal concepts are analyzed to construct the information world of the CPS. The environmental information calculation module uses a back-propagation neural network (BPNN) for classification and pattern recognition. Results:After systematic testing and evaluation, it is found that the PSNR value, NRMSE value, and MAE value of the designed system are excellent, that is, the effectiveness and robustness of the system are high. The temperature control ability of the system is tested. The designed system is good at detecting temperatures and the corresponding situations, so the intelligent CPS can meet the indoor temperature response requirements. Conclusion:This research on the combination of a CPS and artificial intelligence in the construction industry can provide a theoretical basis and practical reference materials for the development of the intelligent construction industry.