scholarly journals Surrogate-assisted Genetic Programming with Simplified Models for Automated Design of Dispatching Rules

2020 ◽  
Author(s):  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Production Systems ◽  
Automated Design ◽  
Research Topic ◽  
Dispatching Rules ◽  
Design System ◽  
Computational Costs ◽  
Powerful Approach ◽  
Effectiveness And Efficiency

© 2013 IEEE. Automated design of dispatching rules for production systems has been an interesting research topic over the last several years. Machine learning, especially genetic programming (GP), has been a powerful approach to dealing with this design problem. However, intensive computational requirements, accuracy and interpretability are still its limitations. This paper aims at developing a new surrogate assisted GP to help improving the quality of the evolved rules without significant computational costs. The experiments have verified the effectiveness and efficiency of the proposed algorithms as compared to those in the literature. Furthermore, new simplification and visualisation approaches have also been developed to improve the interpretability of the evolved rules. These approaches have shown great potentials and proved to be a critical part of the automated design system.

scholarly journals Surrogate-assisted Genetic Programming with Simplified Models for Automated Design of Dispatching Rules

2020 ◽  
Author(s):  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Production Systems ◽  
Automated Design ◽  
Research Topic ◽  
Dispatching Rules ◽  
Design System ◽  
Computational Costs ◽  
Powerful Approach ◽  
Effectiveness And Efficiency

© 2013 IEEE. Automated design of dispatching rules for production systems has been an interesting research topic over the last several years. Machine learning, especially genetic programming (GP), has been a powerful approach to dealing with this design problem. However, intensive computational requirements, accuracy and interpretability are still its limitations. This paper aims at developing a new surrogate assisted GP to help improving the quality of the evolved rules without significant computational costs. The experiments have verified the effectiveness and efficiency of the proposed algorithms as compared to those in the literature. Furthermore, new simplification and visualisation approaches have also been developed to improve the interpretability of the evolved rules. These approaches have shown great potentials and proved to be a critical part of the automated design system.

scholarly journals A Hybrid Genetic Programming Algorithm for Automated Design of Dispatching Rules

2019 ◽  
Vol 27 (3) ◽  
pp. 467-496 ◽  
Author(s):  
Su Nguyen ◽  
Yi Mei ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Job Shop ◽  
Job Shop Scheduling ◽  
Production Systems ◽  
Search Space ◽  
Automated Design ◽  
Dispatching Rules ◽  
Programming Algorithm ◽  
Local Search Heuristic

Designing effective dispatching rules for production systems is a difficult and time-consuming task if it is done manually. In the last decade, the growth of computing power, advanced machine learning, and optimisation techniques has made the automated design of dispatching rules possible and automatically discovered rules are competitive or outperform existing rules developed by researchers. Genetic programming is one of the most popular approaches to discovering dispatching rules in the literature, especially for complex production systems. However, the large heuristic search space may restrict genetic programming from finding near optimal dispatching rules. This article develops a new hybrid genetic programming algorithm for dynamic job shop scheduling based on a new representation, a new local search heuristic, and efficient fitness evaluators. Experiments show that the new method is effective regarding the quality of evolved rules. Moreover, evolved rules are also significantly smaller and contain more relevant attributes.

scholarly journals A Hybrid Genetic Programming Algorithm for Automated Design of Dispatching Rules

2020 ◽  
Author(s):  
Su Nguyen ◽  
Yi Mei ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Job Shop ◽  
Job Shop Scheduling ◽  
Production Systems ◽  
Search Space ◽  
Automated Design ◽  
Dispatching Rules ◽  
Programming Algorithm ◽  
Massachusetts Institute Of Technology ◽  
Institute Of Technology

© 2018 Massachusetts Institute of Technology. Designing effective dispatching rules for production systems is a difficult and timeconsuming task if it is done manually. In the last decade, the growth of computing power, advanced machine learning, and optimisation techniques has made the automated design of dispatching rules possible and automatically discovered rules are competitive or outperform existing rules developed by researchers. Genetic programming is one of the most popular approaches to discovering dispatching rules in the literature, especially for complex production systems. However, the large heuristic search space may restrict genetic programming from finding near optimal dispatching rules. This article develops a new hybrid genetic programming algorithm for dynamic job shop scheduling based on a new representation, a new local search heuristic, and efficient fitness evaluators. Experiments show that the new method is effective regarding the quality of evolved rules. Moreover, evolved rules are also significantly smaller and contain more relevant attributes.

scholarly journals A Hybrid Genetic Programming Algorithm for Automated Design of Dispatching Rules

2020 ◽  
Author(s):  
Su Nguyen ◽  
Yi Mei ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Job Shop ◽  
Job Shop Scheduling ◽  
Production Systems ◽  
Search Space ◽  
Automated Design ◽  
Dispatching Rules ◽  
Programming Algorithm ◽  
Massachusetts Institute Of Technology ◽  
Institute Of Technology

© 2018 Massachusetts Institute of Technology. Designing effective dispatching rules for production systems is a difficult and timeconsuming task if it is done manually. In the last decade, the growth of computing power, advanced machine learning, and optimisation techniques has made the automated design of dispatching rules possible and automatically discovered rules are competitive or outperform existing rules developed by researchers. Genetic programming is one of the most popular approaches to discovering dispatching rules in the literature, especially for complex production systems. However, the large heuristic search space may restrict genetic programming from finding near optimal dispatching rules. This article develops a new hybrid genetic programming algorithm for dynamic job shop scheduling based on a new representation, a new local search heuristic, and efficient fitness evaluators. Experiments show that the new method is effective regarding the quality of evolved rules. Moreover, evolved rules are also significantly smaller and contain more relevant attributes.

Design of machine-building workshops and sites

2018 ◽  
Author(s):  
Анатолий Бойко ◽  
Anatoliy Boyko ◽  
Анатолий Погонин ◽  
Anatoliy Pogonin ◽  
Александр Афанасьев ◽  
...  
Keyword(s):  
Theoretical Basis ◽  
Production Systems ◽  
Automated Design ◽  
Machine Building ◽  
Design System ◽  
Mechanical Assembly ◽  
Structural Units ◽  
Building Enterprise

The textbook "Designing of machine-building workshops and sites" is a publication created on the basis of a modern methodology for designing production systems with specified properties, using an automated design system. Since the main structural units of the machine-building enterprise are mechanical and Assembly shops and sites, so they are paid special attention in the textbook. The theoretical basis of the discipline blended with a large amount of calculations of stalemate machining and mechanical Assembly processes, personnel, production prompdy and examples of designing the different purpose areas.

scholarly journals Automated synthesis of mechanical vibration absorbers using genetic programming

2008 ◽  
Vol 22 (3) ◽  
pp. 207-217 ◽  
Author(s):  
Jianjun Hu ◽  
Erik D. Goodman ◽  
Shaobo Li ◽  
Ronald Rosenberg
Keyword(s):  
Genetic Programming ◽  
Digital Circuits ◽  
Mechanical Vibration ◽  
Automated Design ◽  
Design System ◽  
Vibration Absorbers ◽  
Bond Graphs ◽  
Conceptual Innovation ◽  
Design Systems ◽  
Better Than

AbstractConceptual innovation in mechanical engineering design has been extremely challenging compared to the wide applications of automated design systems in digital circuits. This paper presents an automated methodology for open-ended synthesis of mechanical vibration absorbers based on genetic programming and bond graphs. It is shown that our automated design system can automatically evolve passive vibration absorbers that have performance equal to or better than the standard passive vibration absorbers invented in 1911. A variety of other vibration absorbers with competitive performance are also evolved automatically using a desktop PC in less than 10 h.

scholarly journals A Personalized Machine-Learning-Enabled Method for Efficient Research in Ethnopharmacology. The Case of the Southern Balkans and the Coastal Zone of Asia Minor

2021 ◽  
Vol 11 (13) ◽  
pp. 5826
Author(s):  
Evangelos Axiotis ◽  
Andreas Kontogiannis ◽  
Eleftherios Kalpoutzakis ◽  
George Giannakopoulos
Keyword(s):  
Machine Learning ◽  
Coastal Zone ◽  
Extraction Process ◽  
Asia Minor ◽  
Efficiency And Effectiveness ◽  
Effectiveness And Efficiency ◽  
Intelligent Tools ◽  
Southern Balkans

Ethnopharmacology experts face several challenges when identifying and retrieving documents and resources related to their scientific focus. The volume of sources that need to be monitored, the variety of formats utilized, and the different quality of language use across sources present some of what we call “big data” challenges in the analysis of this data. This study aims to understand if and how experts can be supported effectively through intelligent tools in the task of ethnopharmacological literature research. To this end, we utilize a real case study of ethnopharmacology research aimed at the southern Balkans and the coastal zone of Asia Minor. Thus, we propose a methodology for more efficient research in ethnopharmacology. Our work follows an “expert–apprentice” paradigm in an automatic URL extraction process, through crawling, where the apprentice is a machine learning (ML) algorithm, utilizing a combination of active learning (AL) and reinforcement learning (RL), and the expert is the human researcher. ML-powered research improved the effectiveness and efficiency of the domain expert by 3.1 and 5.14 times, respectively, fetching a total number of 420 relevant ethnopharmacological documents in only 7 h versus an estimated 36 h of human-expert effort. Therefore, utilizing artificial intelligence (AI) tools to support the researcher can boost the efficiency and effectiveness of the identification and retrieval of appropriate documents.

scholarly journals Robust scheduling and dispatching rules for high-mix collaborative manufacturing systems

2021 ◽  
Author(s):  
Andrea Maria Zanchettin
Keyword(s):  
Manufacturing Systems ◽  
Production Systems ◽  
Adaptive Scheduling ◽  
Dispatching Rules ◽  
Numerical Verification ◽  
Robust Scheduling ◽  
Collaborative Manufacturing ◽  
Processing Times ◽  
Increasing Demand ◽  
Variable Production

AbstractMotivated by the increasing demand of mass customisation in production systems, this paper proposes a robust and adaptive scheduling and dispatching method for high-mix human-robot collaborative manufacturing facilities. Scheduling and dispatching rules are derived to optimally track the desired production within the mix, while handling uncertainty in job processing times. The sequencing policy is dynamically adjusted by online forecasting the throughput of the facility as a function of the scheduling and dispatching rules. Numerical verification experiments confirm the possibility to accurately track highly variable production requests, despite the uncertainty of the system.

Criteria and indicators associated with adaptation to the educational process of first-year students at the university

2021 ◽  
pp. 87-93
Author(s):  
Evgeniya N. Popova
Keyword(s):  
Research Topic ◽  
Educational Process ◽  
First Year ◽  
Higher Education Research ◽  
Adaptation Process ◽  
Adaptive Potential ◽  
First Year Students ◽  
Self Development ◽  
The University

The issue of adaptation of modern first-year students to the educational process at the university is one of the current pedagogical tasks. Successful adaptation significantly affects the quality of received education, the degree of formation of personal and professional qualities, contributes to the development of motivation, self-education, and self-development. The purpose of the research is to substantiate the criteria, indicators, and levels of adaptation of first-year students to the learning process at the university. The material for the study was the domestic scientific sources of studying the peculiarities of the adaptation process of students to educational activities in higher education. Research methods: analysis and generalization of psychological-pedagogical and educational-methodical literature on the research topic. We determine as the main criteria for the adaptation of first-year students to the university, the adaptive potential and professionally important qualities of students, consider these concepts, their structure, and their basic properties. On the basis of the analysis and generalization of the existing indicators of the implementation of the adaptive potential, we formulate the author's indicators for determining the level of its development. The degree of formation of professionally important qualities of students are low, medium, and high levels of development of emotional intelligence, negative communicative attitude, intellectual lability, and stress tolerance.

Sign in / Sign up

Export Citation Format

Share Document