Markov Chain

Assembly Line

🧠🗓️ Explainable production planning under partial observability in high-precision manufacturing

📅 Date:

✍️ Authors: Dorina Weichert, Alexander Kister, Peter Volbach, Sebastian Houben, Marcus Trost, Stefan Wrobel

🔖 Topics: Production Planning, Partially Observable Markov Decision Process, Monte Carlo Tree Search, Markov Chain

Conceptually, high-precision manufacturing is a sequence of production and measurement steps, where both kinds of steps require to use non-deterministic models to represent production and measurement tolerances. This paper demonstrates how to effectively represent these manufacturing processes as Partially Observable Markov Decision Processes (POMDP) and derive an offline strategy with state-of-the-art Monte Carlo Tree Search (MCTS) approaches. In doing so, we face two challenges: a continuous observation space and explainability requirements from the side of the process engineers. As a result, we find that a tradeoff between the quantitative performance of the solution and its explainability is required. In a nutshell, the paper elucidates the entire process of explainable production planning: We design and validate a white-box simulation from expert knowledge, examine state-of-the-art POMDP solvers, and discuss our results from both the perspective of machine learning research and as an illustration for high-precision manufacturing practitioners.

Read more at Journal of Manufacturing Systems

Multi-objective optimization of recycling and remanufacturing supply chain logistics network with scalable facility under uncertainty

📅 Date:

✍️ Authors: Yanhua Feng, Xuhui Xia, Lei Wang, Zelin Zhang

🔖 Topics: Sustainability, Recycling, Markov Chain

🏢 Organizations: Wuhan Institute of Science and Technology

Recycling and remanufacturing logistics network affects the scale and efficiency of sustainable development of the manufacturing industry. This paper designs a multi-level closed-loop supply chain network with supplier, manufacturer, recycling centers, preprocessing centers and processing centers. An improved nonlinear grey Bernoulli-Markov model is developed to predict the recycled quantity. The capacity of recycling center and preprocessing center, the demand of manufacturer and the inventory of preprocessing center are formulated as constraints. A dynamic multi-objective model, which is based on scalable logistics facilities, takes into account the minimization of system operating costs and minimization of time costs related to the out-of-stock and inventory in each operating cycle. This model realizes the dynamic selection of the scale of facilities. Objective weighted genetic algorithm is adopted to transform multi-objective optimization problem into a single-objective. A scrap automobile products calculations are analyzed to verify the effectiveness and practicability of this model.

Read more at Taylor and Francis Online

A Markov Chain Formulation for the Grocery Item Picking Process

📅 Date:

✍️ Author: Aditya Athalye

🔖 Topics: markov chain

🏢 Organizations: Walmart

A major chunk of Walmart business (and most of its markets outside the US) comes from Grocery. Customers place orders online which are then delivered to the shipping address or collected by customers from the store (CnC).

What is common to both modes of fulfillment of an order?

It is the process of picking items done by associates in the store. While the actual process has many complexities like downloading of online orders into the store, figuring out locations of items in store, generation of substitutes, generating optimized number of containers to fulfil an order, generating optimized pickwalks for associates across the store etc., the basic operation performed by the associate is to look at different items in an order (typically between 50–70 items) and add them to the containers.

Read more at Walmart Global Tech