Towards Optimal Assembly Line Order Sequencing with Reinforcement Learning: A Case Study

2020 ◽  
Author(s):  
Saad Shafiq ◽  
Christoph Mayr-Dorn ◽  
Atif Mashkoor ◽  
Alexander Egyed
Keyword(s):  
Reinforcement Learning ◽  
Assembly Line ◽  
Optimal Assembly ◽  
Order Sequencing

Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design

2019 ◽  
Author(s):  
Niclas Ståhl ◽  
Göran Falkman ◽  
Alexander Karlsson ◽  
Gunnar Mathiason ◽  
Jonas Boström
Keyword(s):  
Reinforcement Learning ◽  
Short Term Memory ◽  
De Novo ◽  
De Novo Drug Design ◽  
Generative Process ◽  
New Methods ◽  
Multiparameter Optimization ◽  
Long Short Term Memory ◽  
New Compounds

<p>In medicinal chemistry programs it is key to design and make compounds that are efficacious and safe. This is a long, complex and difficult multi-parameter optimization process, often including several properties with orthogonal trends. New methods for the automated design of compounds against profiles of multiple properties are thus of great value. Here we present a fragment-based reinforcement learning approach based on an actor-critic model, for the generation of novel molecules with optimal properties. The actor and the critic are both modelled with bidirectional long short-term memory (LSTM) networks. The AI method learns how to generate new compounds with desired properties by starting from an initial set of lead molecules and then improve these by replacing some of their fragments. A balanced binary tree based on the similarity of fragments is used in the generative process to bias the output towards structurally similar molecules. The method is demonstrated by a case study showing that 93% of the generated molecules are chemically valid, and a third satisfy the targeted objectives, while there were none in the initial set.</p>

scholarly journals Implementation of a standard work routine using Lean Manufacturing tools: A case Study

2021 ◽  
Vol 28 (1) ◽  
Author(s):  
Diego Michael Cornelius dos Santos ◽  
Bruna Karine dos Santos ◽  
César Gabriel dos Santos
Keyword(s):  
Continuous Improvement ◽  
Lean Manufacturing ◽  
Assembly Line ◽  
Real Data ◽  
Production Methods ◽  
Standard Work ◽  
Technological Advances ◽  
Work Routine ◽  
Constant Improvement

Abstract: Due to technological advances, trade politicies and society's consumption patterns, competitiveness among companies has increased considerably, requiring practices that provide a constant improvement in production indicators and product quality. In this context, the use of Toyota Production System tools, also known as Lean Manufacturing, have a fundamental role in the elimination of waste and continuous improvement of industrial production levels. Thus, this work aims to implement a standardized work routine among employees working in a market of parts in an Agricultural Machinery industry, which lacks production methods. To represent this situation, real data were used, which correspond to the needs of the assembly line, and which served as the basis for the analysis and implementation of a new work routine. The results obtained enabled the creation of a standardized work routine, which was obtained by balancing activities between operators and eliminating activities that did not add value to the product.

A Reinforcement Learning - Great-Deluge Hyper-Heuristic for Examination Timetabling

2010 ◽  
Vol 1 (1) ◽  
pp. 39-59 ◽  
Author(s):  
Ender Özcan ◽  
Mustafa Misir ◽  
Gabriela Ochoa ◽  
Edmund K. Burke
Keyword(s):  
Reinforcement Learning ◽  
Complete Solution ◽  
Examination Timetabling ◽  
Low Level ◽  
Termination Criteria ◽  
Candidate Solution ◽  
Wide Range ◽  
Finite Set ◽  
Different Characteristics

Hyper-heuristics can be identified as methodologies that search the space generated by a finite set of low level heuristics for solving search problems. An iterative hyper-heuristic framework can be thought of as requiring a single candidate solution and multiple perturbation low level heuristics. An initially generated complete solution goes through two successive processes (heuristic selection and move acceptance) until a set of termination criteria is satisfied. A motivating goal of hyper-heuristic research is to create automated techniques that are applicable to a wide range of problems with different characteristics. Some previous studies show that different combinations of heuristic selection and move acceptance as hyper-heuristic components might yield different performances. This study investigates whether learning heuristic selection can improve the performance of a great deluge based hyper-heuristic using an examination timetabling problem as a case study.

Improved moth flame optimization algorithm to optimize cost-oriented two-sided assembly line balancing

2019 ◽  
Vol 37 (2) ◽  
pp. 638-663
Author(s):  
Mohd Fadzil Faisae Ab. Rashid ◽  
Ahmad Nasser Mohd Rose ◽  
Nik Mohd Zuki Nik Mohamed ◽  
Fadhlur Rahman Mohd Romlay
Keyword(s):  
Assembly Line ◽  
Assembly Line Balancing ◽  
Line Balancing ◽  
Benchmark Problems ◽  
Labor Costs ◽  
Power Cost ◽  
Content Type ◽  
Set Up ◽  
Line Design

Purpose This paper aims to propose an improved Moth Flame Optimization (I-MFO) algorithm to optimize the cost-oriented two-sided assembly line balancing (2S-ALB). Prior to the decision to assemble a new product, the manufacturer will carefully study and optimize the related cost to set up and run the assembly line. For the first time in ALB, the power cost is modeled together with the equipment, set up and labor costs. Design/methodology/approach I-MFO was proposed by introducing a global reference flame mechanism to guide the global search direction. A set of benchmark problems was used to test the I-MFO performance. Apart from the benchmark problems, a case study from a body shop assembly was also presented. Findings The computational experiment indicated that the I-MFO obtained promising results compared to comparison algorithms, which included the particle swarm optimization, Cuckoo Search and ant colony optimization. Meanwhile, the results from the case study showed that the proposed cost-oriented 2S-ALB model was able to assist the manufacturer in making better decisions for different planning periods. Originality/value The main contribution of this work is the global reference flame mechanism for MFO algorithm. Furthermore, this research introduced a new cost-oriented model that considered power consumption in the assembly line design.

Sign in / Sign up

Export Citation Format

Share Document