DYNAMIC SCHEDULING OF MANUFACTURING SYSTEMS WITH MACHINE LEARNING

2001 ◽  
Vol 12 (06) ◽  
pp. 751-762 ◽  
Author(s):  
PAOLO PRIORE ◽  
DAVID DE LA FUENTE ◽  
ALBERTO GOMEZ ◽  
JAVIER PUENTE
Keyword(s):  
Machine Learning ◽  
Manufacturing Systems ◽  
Job Shop ◽  
Dynamic Scheduling ◽  
Flow Shop ◽  
Dispatching Rules ◽  
Heuristic Rules ◽  
Learning Program ◽  
Training Examples ◽  
Definition Of

A common way of scheduling jobs dynamically in a manufacturing system is by means of dispatching rules. The drawback of this method is that the performance of these rules depends on the state the system is in at each moment, and no one rule exists that overrules the rest in all the possible states that the system may be in. It would therefore be interesting to use the most appropriate rule at each moment. To achieve this goal, a scheduling approach which uses machine learning is presented in this paper. The methodology proposed in this paper may be divided into five basic steps. Firstly, definition of the appropriate control attributes for identifying the relevant manufacturing patterns. In second place, creation of a set of training examples using different values of the control attributes. Subsequently, acquiring of heuristic rules by means of a machine learning program. Then, using of the previously calculated heuristic rules to select the most appropriate dispatching rules, and finally testing of the performance of the approach. The approach that we propose is applied to a flow shop system and to a classic job shop configuration. The results demonstrate that this approach produces an improvement in the performance of the system when compared to the traditional method of using dispatching rules.

scholarly journals Dynamic scheduling of manufacturing systems using machine learning: An updated review

2014 ◽  
Vol 28 (1) ◽  
pp. 83-97 ◽  
Author(s):  
Paolo Priore ◽  
Alberto Gómez ◽  
Raúl Pino ◽  
Rafael Rosillo
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Manufacturing Systems ◽  
Manufacturing System ◽  
Dynamic Scheduling ◽  
The State ◽  
Dispatching Rules ◽  
Dispatching Rule ◽  
Training Examples

AbstractA common way of dynamically scheduling jobs in a manufacturing system is by implementing dispatching rules. The issues with this method are that the performance of these rules depends on the state the system is in at each moment and also that no “ideal” single rule exists for all the possible states that the system may be in. Therefore, it would be interesting to use the most appropriate dispatching rule for each instance. To achieve this goal, a scheduling approach that uses machine learning can be used. Analyzing the previous performance of the system (training examples) by means of this technique, knowledge is obtained that can be used to decide which is the most appropriate dispatching rule at each moment in time. In this paper, a literature review of the main machine learning based scheduling approaches from the last decade is presented.

A review of machine learning in dynamic scheduling of flexible manufacturing systems

2001 ◽  
Vol 15 (3) ◽  
pp. 251-263 ◽  
Author(s):  
PAOLO PRIORE ◽  
DAVID DE LA FUENTE ◽  
ALBERTO GOMEZ ◽  
JAVIER PUENTE
Keyword(s):  
Machine Learning ◽  
Flexible Manufacturing ◽  
Flexible Manufacturing Systems ◽  
Manufacturing Systems ◽  
Manufacturing System ◽  
Flexible Manufacturing System ◽  
Dynamic Scheduling ◽  
Dispatching Rule ◽  
Training Examples ◽  
Better Than

A common way of dynamically scheduling jobs in a flexible manufacturing system (FMS) is by means of dispatching rules. The problem of this method is that the performance of these rules depends on the state the system is in at each moment, and no single rule exists that is better than the rest in all the possible states that the system may be in. It would therefore be interesting to use the most appropriate dispatching rule at each moment. To achieve this goal, a scheduling approach which uses machine learning can be used. Analyzing the previous performance of the system (training examples) by means of this technique, knowledge is obtained that can be used to decide which is the most appropriate dispatching rule at each moment in time. In this paper, a review of the main machine learning-based scheduling approaches described in the literature is presented.

And The World Came To See: New Manufacturing System Designs and Industrial Revolutions

2002 ◽  
Author(s):  
J. T. Black ◽  
David S. Cochran
Keyword(s):  
System Design ◽  
Systems Engineering ◽  
Lean Manufacturing ◽  
Manufacturing Systems ◽  
Manufacturing System ◽  
Job Shop ◽  
Flow Shop ◽  
The World ◽  
Industrial Revolutions ◽  
New System

AND THE WORLD CAME TO SEE. When a new manufacturing system design (MSD) is developed by a company or a group of companies, the rest of the world comes to those factories to learn about the new system. In the last 200 years, three new factory designs have evolved, called the job shop, the flow shop and the lean shop. Each is based on a new system design — a functional design, a product flow design and a linked cell design. New factory designs lead to new industrial leaders and even new industrial revolutions (IR’s). Two appendixes are included: One outlines the implementation strategy for the lean shop and the other is a discussion of lean manufacturing from the viewpoint of K. Hitomi, Japanese professor of manufacturing systems engineering.

scholarly journals Novel Complexity Indicator of Manufacturing Process Chains and Its Relations to Indirect Complexity Indicators

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Vladimir Modrak ◽  
Zuzana Soltysova
Keyword(s):  
Manufacturing Process ◽  
Material Flow ◽  
Manufacturing Systems ◽  
Job Shop ◽  
Flow Shop ◽  
Manufacturing Processes ◽  
Process Chains

Manufacturing systems can be considered as a network of machines/workstations, where parts are produced in flow shop or job shop environment, respectively. Such network of machines/workstations can be depicted as a graph, with machines as nodes and material flow between the nodes as links. The aim of this paper is to use sequences of operations and machine network to measure static complexity of manufacturing processes. In this order existing approaches to measure the static complexity of manufacturing systems are analyzed and subsequently compared. For this purpose, analyzed competitive complexity indicators were tested on two different manufacturing layout examples. A subsequent analysis showed relevant potential of the proposed method.

scholarly journals A Computational Study of Representations in Genetic Programming to Evolve Dispatching Rules for the Job Shop Scheduling Problem

2020 ◽  
Author(s):  
S Nguyen ◽  
Mengjie Zhang ◽  
M Johnston ◽  
K Chen Tan
Keyword(s):  
Genetic Programming ◽  
Manufacturing Systems ◽  
Job Shop ◽  
Job Shop Scheduling ◽  
Computational Study ◽  
Dispatching Rules ◽  
Scheduling Problem ◽  
Learning Approaches ◽  
Job Shop Scheduling Problem ◽  
Shop Scheduling

Designing effective dispatching rules is an important factor for many manufacturing systems. However, this time-consuming process has been performed manually for a very long time. Recently, some machine learning approaches have been proposed to support this task. In this paper, we investigate the use of genetic programming for automatically discovering new dispatching rules for the single objective job shop scheduling problem (JSP). Different representations of the dispatching rules in the literature are newly proposed in this paper and are compared and analysed. Experimental results show that the representation that integrates system and machine attributes can improve the quality of the evolved rules. Analysis of the evolved rules also provides useful knowledge about how these rules can effectively solve JSP. © 1997-2012 IEEE.

A DYNAMIC APPROACH OF USING DISPATCHING RULES IN SCHEDULING

2016 ◽  
Vol 78 (6) ◽  
Author(s):  
Khaled Ali Abuhasel
Keyword(s):  
Processing Time ◽  
Job Shop ◽  
Flow Shop ◽  
Job Shop Scheduling ◽  
Working Environment ◽  
Dispatching Rules ◽  
Scheduling Problems ◽  
Changing Environment ◽  
Environment Simulation ◽  
Made In

Manufacturing system in reality has dynamic nature due to certain unexpected events occur in changing environment, which requires rescheduling. This does not mean that every decision is made in real time. Based on the state of the working environment, determining best rule at right time is one of the alternatives.  This study focuses on selecting the dispatching rule that show best performance dynamically both in static and changing environment.  Simulation is carried out by employing genetic algorithm on flow-shop and job-shop scheduling problems to compare the performance of the dispatching rules dynamically. Out of many rules proposed in the past, it has been observed that under certain conditions, the SPT (shortest processing time) performs best in both the environment, when the total processing time of a job is not high relatively.  

A Data-Driven Proactive Scheduling Approach for Hybrid Flow Shop Scheduling Problem

2021 ◽  
Author(s):  
Dong Han ◽  
Wangming Li ◽  
Xinyu Li ◽  
Liang Gao ◽  
Yang Li
Keyword(s):  
Manufacturing Systems ◽  
Dynamic Scheduling ◽  
Flow Shop ◽  
Intelligent Manufacturing ◽  
Data Driven ◽  
Hybrid Flow Shop ◽  
Shop Scheduling ◽  
Dynamic Events ◽  
Proactive Scheduling ◽  
Hybrid Flow Shop Scheduling

Abstract As we all know, the COVID-19 pandemic brought a great challenge to manufacturing industry, especially for some traditional and unstable manufacturing systems. It reminds us that intelligent manufacturing certainly will play a key role in the future. Dynamic shop scheduling is also an inevitable hot topic in intelligent manufacturing. However, traditional dynamic scheduling is a kind of passive scheduling mode which takes measures to adjust disturbed scheduling processes after the occurrence of dynamic events. It is difficult to ensure the stability of production because of lack of proactivity. To overcome these shortcomings, manufacturing big data and data technologies as the core driving force of intelligent manufacturing will be used to guide production. Thus, a data-driven proactive scheduling approach is proposed to deal with the dynamic events, especially for machine breakdown. In this paper, the overall procedure of the proposed approach is introduced. More specifically, we first use collected manufacturing data to predict the occurrence of machine breakdowns and provide reliable input for dynamic scheduling. Then a proactive scheduling model is constructed for the hybrid flow shop problem, and an intelligent optimization algorithm is used to solve the problem to realize proactive scheduling. Finally, we design comparative experiments with two traditional rescheduling strategies to verify the effectiveness and stability of the proposed approach.

Acquisition of Dispatching Rules for Job-Shop Scheduling Problem by Artificial Neural Networks Using PSO

2013 ◽  
Vol 17 (5) ◽  
pp. 731-738 ◽  
Author(s):  
Yasumasa Tamura ◽  
◽  
Masahito Yamamoto ◽  
Ikuo Suzuki ◽  
Masashi Furukawa ◽  
...  
Keyword(s):  
Manufacturing Systems ◽  
Job Shop ◽  
Job Shop Scheduling ◽  
Dispatching Rules ◽  
Scheduling Problem ◽  
Job Shop Scheduling Problem ◽  
Shop Scheduling ◽  
Artificial Neural ◽  
Feature Values ◽  
Artificial Neural Network Ann

A Job-shop Scheduling Problem (JSP) constitutes the basic scheduling problem that is observed in manufacturing systems. In conventional JSP, feature values of work and queue times are used to formulate dispatching rules for scheduling. In this paper, an Artificial Neural Network (ANN) is used to create an index for job priority. Furthermore, in order to optimize the output of the ANN, Particle Swarm Optimization (PSO) is used in unsupervised learning of the synaptic weights for the ANN. The functions of the proposed method are discussed in this paper.

Maintenance on Job Shop Industry: Review and Analysis

2016 ◽  
Vol 842 ◽  
pp. 365-372 ◽  
Author(s):  
Herman Budi Harja ◽  
Tri Prakosa ◽  
Yatna Yuwana Martawirya
Keyword(s):  
Manufacturing Systems ◽  
Job Shop ◽  
Flow Shop ◽  
Dynamic Condition ◽  
Maintenance Optimization ◽  
Reliability Growth ◽  
Monitoring Cost ◽  
Reliability Modeling ◽  
Maintenance Schedule ◽  
Reliability Improvement

This paper presents overviews about reliability and maintainability of equipment especially for job-shop manufacturing systems. The job shop industry has the characteristics of a more dynamic production than flow shop industries, where products with a variety of great but small amounts. Its dynamic condition certainly contributes directly to the failure rate and reliability growth of equipment. Therefore, proper maintenance should be done as the reliability improvement. Stages of reliability improvement are reliability modeling, reliability analysis and maintenance optimization. This stage is based on reliability growth of equipment that is indicated the deterioration process of failure components, it can be build from maintenance data history or condition data monitoring.. Cost is often considered in points of a maintenance schedule. This cost was affected by minimizing the negative effects of maintenance and maximizing the benefit of production. The attention at reliability and maintenance optimization is a well researches area until now. This paper presents a brief review of existing reliability and maintenance research. Several reliable methods in this area are discussed and maintenance on job-shop industry as future prospects is investigated. It is shown in this paper that some aspect in the area of maintenance on job-shop industry steel needs to be deeply developed.

Hyper-heuristic Evolution of Dispatching Rules: A Comparison of Rule Representations

2015 ◽  
Vol 23 (2) ◽  
pp. 249-277 ◽  
Author(s):  
Jürgen Branke ◽  
Torsten Hildebrandt ◽  
Bernd Scholz-Reiter
Keyword(s):  
Neural Network ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Manufacturing Systems ◽  
Job Shop ◽  
Dispatching Rules ◽  
Tree Representation ◽  
Linear Representations ◽  
The Neural Network ◽  
Dynamic Stochastic

Dispatching rules are frequently used for real-time, online scheduling in complex manufacturing systems. Design of such rules is usually done by experts in a time consuming trial-and-error process. Recently, evolutionary algorithms have been proposed to automate the design process. There are several possibilities to represent rules for this hyper-heuristic search. Because the representation determines the search neighborhood and the complexity of the rules that can be evolved, a suitable choice of representation is key for a successful evolutionary algorithm. In this paper we empirically compare three different representations, both numeric and symbolic, for automated rule design: A linear combination of attributes, a representation based on artificial neural networks, and a tree representation. Using appropriate evolutionary algorithms (CMA-ES for the neural network and linear representations, genetic programming for the tree representation), we empirically investigate the suitability of each representation in a dynamic stochastic job shop scenario. We also examine the robustness of the evolved dispatching rules against variations in the underlying job shop scenario, and visualize what the rules do, in order to get an intuitive understanding of their inner workings. Results indicate that the tree representation using an improved version of genetic programming gives the best results if many candidate rules can be evaluated, closely followed by the neural network representation that already leads to good results for small to moderate computational budgets. The linear representation is found to be competitive only for extremely small computational budgets.

Sign in / Sign up

Export Citation Format

Share Document