Mechanical discontinuity embedded in a material plays an essential role in determining the bulk mechanical, physical, and chemical properties. The ability to control mechanical discontinuity is relevant for industries dependent on natural, synthetic and composite materials, e.g. construction, aerospace, oil and gas, ceramics, metal, and geothermal industries, to name a few. The paper is a proof-of-concept development and deployment of a reinforcement learning framework to control the propagation of mechanical discontinuity. The reinforcement learning framework is coupled with an OpenAI-Gym-based environment that uses the mechanistic equation governing the propagation of mechanical discontinuity. Learning agent does not explicitly know about the underlying physics of propagation of discontinuity; nonetheless, the learning agent can infer the control strategy by continuously interacting the simulation environment. The Markov decision process, which includes state, action and reward, had to be carefully designed to obtain a good control policy. The deep deterministic policy gradient (DDPG) algorithm is implemented for learning continuous actions for the desired reinforcement learning. It is also observed that the training efficiency is strongly determined by the formulation of reward function. An adaptive reward function involving reward shaping improves the training. The reward function that forces the learning agent to stay on the shortest linear path between crack tip and goal point performs much better than the reward function that aims to reach closest to the goal point in minimum number of steps. After close to 500 training episodes, the reinforcement learning framework successfully controlled the propagation of discontinuity in a material despite the complexity of the propagation pathway determined by multiple goal points.

Mechanical discontinuity embedded in a material plays an essential role in determining the bulk mechanical, physical, and chemical properties. This paper is a proof-of-concept development and deployment of a reinforcement learning framework to control both the direction and rate of the growth of fatigue crack. The reinforcement learning framework is coupled with an OpenAI-Gym-based environment that implements the mechanistic equations governing the fatigue crack growth. Learning agent does not explicitly know about the underlying physics; nonetheless, the learning agent can infer the control strategy by continuously interacting the numerical environment. The Markov decision process, which includes state, action and reward, is carefully designed to obtain a good control policy. The deep deterministic policy gradient algorithm is implemented for learning the continuous actions required to control the fatigue crack growth. An adaptive reward function involving reward shaping improves the training. The reward is mostly positive to encourage the learning agent to keep accumulating the reward rather than terminate early to avoid receiving high accumulated penalties. An additional high reward is given to the learning agent when the crack tip reaches close enough to the goal point within specific training iterations to encourage the agent to reach the goal points as quickly as possible rather than slowly approaching the goal point to accumulate the positive reward. The reinforcement learning framework can successfully control the fatigue crack propagation in a material despite the complexity of the propagation pathway determined by multiple goal points.