Search for: All records

Industry 4.0 drives exponential growth in the amount of operational data collected in factories. These data are commonly distributed and stored in different business units or cooperative companies. Such data-rich environments increase the likelihood of cyber attacks, privacy breaches, and security violations. Also, this poses significant challenges on analytical computing on sensitive data that are distributed among different business units. To fill this gap, this article presents a novel privacy-preserving framework to enable federated learning on siloed and encrypted data for smart manufacturing. Specifically, we leverage fully homomorphic encryption (FHE) to allow for computation on ciphertexts and generate encrypted results that, when decrypted, match the results of mathematical operations performed on the plaintexts. Multilayer encryption and privacy protection reduce the likelihood of data breaches while maintaining the prediction performance of analytical models. Experimental results in real-world case studies show that the proposed framework yields superior performance to reduce the risk of cyber attacks and harness siloed data for smart manufacturing.

 

The new wave of Industry 4.0 is transforming manufacturing factories into data-rich environments. This provides an unprecedented opportunity to feed large amounts of sensing data collected from the physical factory into the construction of digital twin (DT) in cyberspace. However, little has been done to fully utilize the DT technology to improve the smartness and autonomous levels of small and medium-sized manufacturing factories. Indeed, only a small fraction of small and medium-sized manufacturers (SMMs) has considered implementing DT technology. There is an urgent need to exploit the full potential of data analytics and simulation-enabled DTs for advanced manufacturing. Hence, this paper presents the design and development of DT models for simulation optimization of manufacturing process flows. First, we develop a multi-agent simulation model that describes nonlinear and stochastic dynamics among a network of interactive manufacturing things, including customers, machines, automated guided vehicles (AGVs), queues, and jobs. Second, we propose a statistical metamodeling approach to design sequential computer experiments to optimize the utilization of AGV under uncertainty. Third, we construct two new graph models—job flow graph and AGV traveling graph—to track and monitor the real-time performance of manufacturing jobshops. The proposed simulation-enabled DT approach is evaluated and validated with experimental studies for the representation of a real-world manufacturing factory. Experimental results show that the proposed methodology effectively transforms a manufacturing jobshop into a new generation of DT-enabled smart factories. The sequential design of experiments effectively reduces the computation overhead of expensive simulations while optimally scheduling the AGV to achieve production throughput cost-effectively. This research is strongly promised to help SMMs fully utilize big data and DT technology for gaining competitive advantages in the global marketplace.

 

Advanced sensing and cloud systems propel the rapid advancements of service-oriented smart manufacturing. As a result, there is widespread generation and proliferation of data in the interest of manufacturing analytics. The sheer amount and velocity of data have also attracted a myriad of malicious parties, unfortunately resulting in an elevated prevalence of cyber-attacks whose impacts are only gaining in severity. Therefore, this article presents a new distributed cryptosystem for analytical computing on encrypted data in the manufacturing environment, with a case study on manufacturing resource planning. This framework harmonizes Paillier cryptography with the Alternating Direction Method of Multipliers (ADMM) for decentralized computation on encrypted data. Security analysis shows that the proposed Paillier-ADMM system is resistant to attacks from external threats, as well as privacy breaches from trusted-but-curious third parties. Experimental results show that smart allocation is more cost-effective than the benchmarked deterministic and stochastic policies. The proposed distributed cryptosystem shows strong potential to leverage the distributed data for manufacturing intelligence, while reducing the risk of data breaches. 

Public emergencies pose catastrophic casualties and financial losses in densely populated areas, rendering communities such as cities, towns, and universities particularly susceptible due to their intricate environments and high pedestrian traffic. While simulation analysis offers a flexible and cost-effective approach to evaluating evacuation procedures, conventional evacuation models are often limited to specific scenarios and communities, overlooking the diverse range of emergencies and evacuee behaviors. Thus, there is an urgent need for an evacuation model capable of capturing complex structures of communities and modeling evacuee responses to various emergencies. This paper presents a novel approach to simulating responsive evacuation behaviors for multiple emergency situations in public communities through spatial network modeling and multi-agent modeling. Leveraging a community network framework adaptable to different community layouts based on map data, the proposed model employs a multi-agent approach to characterize responsive and decentralized evacuation decision-making. Experimental results show the model’s efficacy in representing pedestrian flow and pedestrians’ reactive behavior across various campuses based on real-world map data. Additionally, the case study highlights the potential of the proposed model to simulate pedestrian dynamics for a variety of heterogeneous emergencies. The proposed community evacuation model holds strong promise for evaluating evacuation policies and providing insights into resilient plans during public emergencies, thereby enhancing community safety.