The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making(IDM)systems.Consequently,IDM shoul...The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making(IDM)systems.Consequently,IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications.The advancement of Artificial General Intelligence(AGI)that transcends task and application boundaries is critical for enhancing IDM.Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks,including computer vision,natural language processing,and reinforcement learning.We propose that a Foundation Decision Model(FDM)can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture,offering a promising solution for expanding IDM applications in complex real-world situations.In this paper,we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI,production scheduling,and robotics tasks.Lastly,we present a case study demonstrating our FDM implementation,DigitalBrain(DB1)with 1.3 billion parameters,achieving human-level performance in 870 tasks,such as text generation,image captioning,video game playing,robotic control,and traveling salesman problems.As a foundation decision model,DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.展开更多
Aging precipitation behavior and mechanical properties of Inconel 617 superalloy aged at 760℃ for up to 10000 h were investigated. The results showed that the precipitates of the aged alloy are M23C6 and M6C carbides...Aging precipitation behavior and mechanical properties of Inconel 617 superalloy aged at 760℃ for up to 10000 h were investigated. The results showed that the precipitates of the aged alloy are M23C6 and M6C carbides and γ phase. The carbide particles precipitated both at the grain boundaries and within grains, and the γ phase particles were situated at intragranular sites in the process of aging. The carbide particles were discontinuously dispersed at grain boundaries after aging for 3000 h, while after aged for 5000 h the carbide particles are merged. The precipitates inside grains remained stable even after aging for 10000 h. The hardness was increased for the alloy aged for 300 h up to 3000 h, which was resulted primarily from the precipitation of carbides as discrete particles both at the grain boundaries and inside grains. Small quantity γ precipitates were formed inside grains, to some extent, which contributed to an enhanced hardness. However, a decrease of the hardness was observed after aging for 5000 h. A significant drop in toughness of the alloy aged for 300 h was attributed to the reduction of the bonding interface strength when carbides precipitated at grain boundaries. Thereafter, the toughness decreased slowly with the prolonged aging time. The high temperature tensile properties of the aged alloy are rather stable even aged for 300-3000 h.展开更多
文摘The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making(IDM)systems.Consequently,IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications.The advancement of Artificial General Intelligence(AGI)that transcends task and application boundaries is critical for enhancing IDM.Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks,including computer vision,natural language processing,and reinforcement learning.We propose that a Foundation Decision Model(FDM)can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture,offering a promising solution for expanding IDM applications in complex real-world situations.In this paper,we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI,production scheduling,and robotics tasks.Lastly,we present a case study demonstrating our FDM implementation,DigitalBrain(DB1)with 1.3 billion parameters,achieving human-level performance in 870 tasks,such as text generation,image captioning,video game playing,robotic control,and traveling salesman problems.As a foundation decision model,DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.
基金supported by the CSEE Youth Science & Technology Innovation Project (No.003)National Energy Applied Technology Research & Demonstration Project (No.NY20110102-1)
文摘Aging precipitation behavior and mechanical properties of Inconel 617 superalloy aged at 760℃ for up to 10000 h were investigated. The results showed that the precipitates of the aged alloy are M23C6 and M6C carbides and γ phase. The carbide particles precipitated both at the grain boundaries and within grains, and the γ phase particles were situated at intragranular sites in the process of aging. The carbide particles were discontinuously dispersed at grain boundaries after aging for 3000 h, while after aged for 5000 h the carbide particles are merged. The precipitates inside grains remained stable even after aging for 10000 h. The hardness was increased for the alloy aged for 300 h up to 3000 h, which was resulted primarily from the precipitation of carbides as discrete particles both at the grain boundaries and inside grains. Small quantity γ precipitates were formed inside grains, to some extent, which contributed to an enhanced hardness. However, a decrease of the hardness was observed after aging for 5000 h. A significant drop in toughness of the alloy aged for 300 h was attributed to the reduction of the bonding interface strength when carbides precipitated at grain boundaries. Thereafter, the toughness decreased slowly with the prolonged aging time. The high temperature tensile properties of the aged alloy are rather stable even aged for 300-3000 h.
