<p>Shiv Nadar University is a comprehensive, multidisciplinary, research-focused, and student-centric University offering a full range of academic programs at the undergraduate, postgraduate and doctoral level. With state-of-the-art infrastructure, the University comprises of academic wings, sophisticated labs, international standard sports facilities, amphitheaters, auditorium, conference rooms and smart classrooms. The University&rsquo;s goal is to become internationally recognized for the quality of its research and creative endeavors and their applicability to improving quality of life, generating new insights and expanding the boundaries of human knowledge creativity. Committed to excellence in teaching, research and service, the University aims to serve the higher education needs of India and the world beyond.</p>

Shiv Nadar University

Assigning the right task to the right worker remains a challenge to an assembly line manager. This work is proposed to use digital-twin technologies for Assembly line worker assignment and balancing problems (ALWABP) for a collaborative assembly system. Applications of the Internet of Things, Data analytics and Learning algorithms are proposed to estimate the worker's work skill and task performance. Assembly line Digital Twin and collaborative robot (CoBot) work simulation tools are proposed to estimate the CoBot's assembly task performing ability and execution time. ALWABP framework is proposed to optimize the work allocation between the worker and the CoBot. Assembly line digital twin is furthermore proposed to simulate the ALWABP output during the decision-making process of the assembly line manager by considering the Human-in-the-loop decision-making system. Copyright © 2022 The Authors. This is an open access article under the CC BY-NC-ND license.

World University root node

Mechanical Engineering

(SoE) School of Engineering

IFAC-PapersOnLine

A digital-twin based worker's work allocation framework for a collaborative assembly system

This paper addresses the joint optimization model of production scheduling, work-in-process (WIP) inventory control and group preventive maintenance (PM) planning in a multi-machine system with multi-components. The objective is to obtain optimum production sequence, PM intervals and grouping of components, which minimize the total expected cost per unit time of the system. A new meta-heuristic named Jaya algorithm and two popular algorithms viz. simulated annealing (SA) and particle swarm optimization (PSO) are applied to optimize the objective function. Initially, the optimum group of components is obtained based on the integer multiples of individual PM intervals. Secondly, the job permutation sequence incorporating group PM intervals is identified with the largest order value (LOV) rule. The shift in optimum PM intervals is realized with an advanced-postpone balancing approach. Computational results reveal that the proposed integrated model along with group PM yields up to 25% cost reductions when compared to the integrated model with individual maintenance as well as 37% savings while no integration is performed. Furthermore, the performance of algorithms is evaluated with large-sized problems. The obtained results show that Jaya and SA yielded comparable results, however, PSO is least productive. Thus, the proposed approach yields better economic performance and brings more improvised solutions as compared to the conventional methods of integrated scheduling and maintenance optimization problems. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Annals of Operations Research

Joint optimization of production scheduling and group preventive maintenance planning in multi-machine systems

Worker' work-rotation between the workstations of an assembly line is a common task to an assembly line manager, to manage the workload between the assembly line workers. Usually, worker work rotation makes an interruption to a continuous production system. It is a desire of an assembly line manager to avoid the worker's work-rotation, at least between the work breaks. This work aims to protect the manager's interest by predicting the comfortable work-duration time of an assembly line worker for a given work, based on the working condition and the instantaneous physical & mental status of the worker. The comfortable work-duration time can be used during the worker's work assignment to reduce interruptions. Factors, which influence the longevity of workers' comfortable work duration time are identified. IIoT based sensors are proposed here to monitor the relevant factors for diagnostics. Machine Learning techniques are used as a part of prognostics to predict the comfortable work-duration time of a worker, based on his/her physical & mental status. Implementation methodology is explained along with a simulated experiment. © 2022 Elsevier B.V.. All rights reserved.

Procedia CIRP

A Dynamic System to Predict an Assembly Line Worker's Comfortable Work-Duration Time by Using the Machine Learning Technique

The present paper develops an integrated approach for joint optimization of preventive maintenance (PM) planning and quality control policy in a single machine manufacturing system. Considering the economic dependency between quality and maintenance parameters, the proposed model aims to optimize the four decision variables, viz. PM interval, sample size, sample frequency and control limit coefficient to minimize the expected total integrated cost per unit time. The imperfect age-based PM model is applied which addresses the most practical issue that a unit may not always be maintained to an as-good-as-new state. Analysing the problem to be NP-hard in nature, a recently developed meta-heuristic named Jaya algorithm is applied to retrieve the near-optimum solutions. The peculiarity of Jaya as compared to conventional heuristics is that it is a parameter-less algorithm thus does not require tuning to algorithm-specific parameters thereby minimizing computational complexity to a great extent. A numerical example is presented to demonstrate the effectiveness of the integrated economic design of PM and process quality control parameters. Computational results reveal the effectiveness of the proposed approach. © 2022 The Authors. Published by Elsevier B.V.

An Efficient Jaya Algorithm for Joint Optimization of Preventive Maintenance and Quality Policy in Production Systems

It is a difficult task for an assembly line manager to select an appropriate worker from the available workers' list to assign to an assembly line workstation. Since each available worker has a unique set of skills and abilities, this research considers the worker differences in their work performance. The worker's work performance is considered based on their working speed or productivity. Task execution time (TET) is the measure used to distinguish the worker's work performance. The TET prediction is made by the application of a knowledge-based system framework. Workers' historical work-time data is used to model the knowledge objects. Workers are classified as skilled and semi-skilled respective methodologies are given for both categories of workers. Statistical-based learning algorithms are proposed for skilled workers based on the worker's age, gender, and work skill. Similarly, worker's learning patterns are used for semi-skilled workers. The predicted TET is used in solving the assembly line worker assignment problem. The second part of this work is to prioritise the aged worker during the worker selection without increment of worker count. The illustrative example helps understand the scope of the proposed methodology in an assembly line worker assignment problem. © 2022 Elsevier B.V.

International Journal of Production Economics

Modelling and prediction of worker task performance using a knowledge-based system application

Group maintenance deals with performing preventive maintenance (PM) on other components when the system stops due to induced failure or scheduled PM interval of a particular component. Group maintenance actions save downtime costs and other production losses. However, simultaneous maintenance of all units is not always economically beneficial. As a consequence, the decision to which group of components is maintained is very selective due to economic and stochastic interdependencies. In the present paper, we propose a novel and efficient group maintenance model in the multi-unit series system for grouping under PM intervals. The objective is to obtain an optimum group of components and PM intervals which minimizes the expected total maintenance cost of the system per unit time. A recently developed meta-heuristic named teaching–learning-based optimization (TLBO) algorithm is applied to optimize the objective function. The peculiarity of TLBO is that unlike other evolutionary-based heuristics it is a parameterless algorithm which makes it computationally easy to understand and implement. Computational results yield the effectiveness of the proposed approach when compared with traditional maintenance practices. © 2021, Springer Nature Singapore Pte Ltd.

Lecture Notes in Mechanical Engineering

Group Preventive Maintenance Model for Multi-unit Series System: A TLBO Algorithm-Based Approach

This work is an extension part of the Assembly Line Worker Assignment Balancing Problem(ALWABP), aims to provide a dynamic solution for an assembly line fatigue worker job rotation by using machine learning based digital twin. This framework explains, fatigue worker identification and work rotation possibilities for a reconfigurable assembly line. The fatigue causing parameters are sensed from the workers and classified with a fatigue classifier then send the fatigue worker details to a worker job rotation search algorithm. The job rotation search algorithm provides a suggestion to the production supervisor for a best possible worker job rotation/reallocation solution dynamically. © 2021 The Author(s).

A dynamic job rotation scheduling conceptual framework by a human representing digital twin

The Jaya algorithm is a novel, simple, and efficient meta-heuristic optimization technique and has received a successful application in the various fields of engineering and sciences. In the present paper, we apply the Jaya algorithm to permutation flow shop scheduling problem (PFSP) with the multi-objective of minimization of maximum completion time (makespan) and tardiness cost under due date constraints. PFSP is a well-known NP-hard and discrete combinatorial optimization problem. Firstly, to retrieve a job sequence, a random preference is allocated to each job in a permutation schedule. Secondly, a job preference vector is transformed into a job permutation vector by means of largest order value (LOV) rule. To deal with the multi-objective criteria, we apply a multi-attribute model (MAM) based on Apriori approach. The correctness of the Jaya algorithm is verified by comparing the results with the total enumeration method and simulated annealing (SA) algorithm. Computational results reveal that the proposed optimization technique is well efficient in solving multi-objective discrete combinatorial optimization problems such as the flow shop scheduling problem in the present study. © Springer Nature Singapore Pte Ltd. 2020.

Advances in Intelligent Systems and Computing

An Efficient Jaya Algorithm for Multi-objective Permutation Flow Shop Scheduling Problem

Opportunistic maintenance approaches deal with performing group preventive maintenance (PM) on the other units in a series system due to the intervention of any scheduled PM of a component. Simultaneous maintenance actions show better economic performance due to the direct reduction of downtime costs and production losses. However, it is uneconomical to perform maintenance on all units simultaneously. To address this issue, various simulation and optimization approaches including Markov chains, genetic algorithm etc. have been applied in order to achieve optimum solutions in group maintenance models. However, most of these strategies suffer from intractability as the problem size increases. In the present paper, we develop an efficient opportunistic grouping methodology for the multi-unit series system while considering imperfect preventive maintenance. The aim is to obtain an optimum PM interval and grouping of units to minimize the expected total system maintenance cost per unit time during the mission. A recently developed meta-heuristic named ‘Jaya algorithm’ is applied to optimize the objective function. The effectiveness of the proposed approach is examined with three maintenance models: single unit model, mono-group model and the proposed opportunistic group model. Results reveal that the proposed group maintenance model results in 19\% cost savings as compared to the mono-group model and 71\% compared to the single component maintenance model. © 2019, Operational Research Society of India.

OPSEARCH

An opportunistic group maintenance model for the multi-unit series system employing Jaya algorithm

Jaya algorithm has recently been proposed, which is simple and efficient meta-heuristic optimization technique and has received a great attention in the world of optimization. It has been successfully applied to some thermal, design and manufacturing associated optimization problems. This paper aims to analyze the performance of Jaya algorithm for permutation flow-shop scheduling problem which is a well-known NP-hard optimization problem. The objective is to minimize the makespan. First, to make Jaya algorithm adaptive to the problem, a random priority is allocated to each job in a permutation sequence. Second, a job priority vector is converted into job permutation vector by means of Largest Order Value (LOV) rule. An exhaustive comparative study along with statistical analysis is performed by comparing the results with public benchmarks and other competitive heuristics. The key feature of Jaya algorithm of simultaneous movement towards the best solution and going away from the worst solution enables it to avoid being trapped in the local optima. Furthermore, the uniqueness of Jaya algorithm compared with any other evolutionary based optimization technique is that it is totally independent of specific parameters. This substantially reduces the computation effort and numerical complexity. Computational results reveal that Jaya algorithm is efficient in most cases and has considerable potential for permutation flow-shop scheduling problems. © 2020 by the authors; licensee Growing Science, Canada.

Fulltext

International Journal of Industrial Engineering Computations

A discrete jaya algorithm for permutation flow-shop scheduling problem

This paper deals with joint optimization of production scheduling and group maintenance planning in single machine system with multi units arranged in series. The objective is to achieve optimum production sequence, preventive maintenance (PM) intervals and grouping of units which minimize the total integrated cost per unit time of the system. Teaching-Learning Based Optimization (TLBO) algorithm is applied to optimize the objective function. The peculiarity of TLBO as against other algorithms is that it is independent of algorithm specific parameters. The largest order value rule is utilized to retrieve the permutation vector while grouping of units is performed under PM intervals. Computational results reveal the effectiveness of the proposed approach. © 2020 The Authors.

Integration of production scheduling and group maintenance planning in multi-unit system employing TLBO algorithm

This paper deals with permutation flow shop scheduling problem in which an integrated cost model consisting of work-in-process inventory carrying cost and penalty cost due to batch delay is proposed. The objective is to obtain an optimum production schedule which minimizes the expected total cost per unit time of scheduling. To optimize the objective function, we apply two new metaheuristic optimization techniques namely TLBO (teaching-learning based optimization) and Jaya and two traditional algorithms: PSO (particle swarm optimization) and SA (simulated annealing). The problem is solved for several instances ranging from 8 jobs and 5 machines to 500 jobs and 20 machines. Computational results show that for small instances, all algorithms performed equally good when compared with the exact solution (total enumeration method). However, for medium and large size problems, enumeration method was unable to give the results in a reasonable computation time period. Therefore the results of all four algorithms are compared among themselves and found that Jaya outperforms all algorithms. However, for a few large instances, SA yields better results in less computation time as against other heuristics. The overall performance of all algorithms reveals that TLBO and Jaya have considerable potential to solve discrete combinatorial problems such as permutation flow-shop scheduling problems. © 2018 Elsevier Ltd

Computers and Industrial Engineering

A TLBO and a Jaya heuristics for permutation flow shop scheduling to minimize the sum of inventory holding and batch delay costs

Opportunistic maintenance (OM) models take the opportunity of economic dependencies among components in the system when it stops due to failure or scheduled preventive maintenance (PM) of a certain equipment. Performing maintenance actions simultaneously can substantially bring down the maintenance costs in terms of reduced downtime costs, production losses, service and labor costs, etc. However, maintaining all components together may be uneconomical due to over or underutilization. Secondly, most of the study on opportunistic maintenance consider the system comprising of either multi-machines with the single component or single machine with multi-components. Based on this motivation, the present paper proposes an effective opportunistic grouping policy for multi-component multi-machine system considering time-based imperfect PM actions. The imperfect PM addresses the most practical issue that PM does not always return the component to as-good-as-new status. To the best of our knowledge, this is the first attempt to develop the multi-machine OM policy with multi-components. The objective is to obtain an optimum group of components and PM times in order to minimize the total system maintenance cost per unit time during the mission. The opportunistic grouping model is based on the individual component’s PM intervals. Two grouping strategies viz. grouping within the machines and grouping between the machines are adopted in order to identify the diversity of the proposed model. A recently developed meta-heuristic named Jaya algorithm is applied to optimize the objective function. The effectiveness of the proposed model is analyzed with an illustrative example. Results reveal that the proposed model shows better economic performance as compared from the individual maintenance practices. © 2018, Curran Associates Inc. All rights reserved.

Proceedings of International Conference on Computers and Industrial Engineering, CIE

Opportunistic group maintenance policy for multi-machine system with multi-components

This book explores the domain of reliability engineering in the context of machine tools. Failures of machine tools not only jeopardize users' ability to meet their due date commitments but also lead to poor quality of products, slower production, down time losses etc. Poor reliability and improper maintenance of a machine tool greatly increases the life cycle cost to the user. Thus, the application area of the present book, i.e. machine tools, will be equally appealing to machine tool designers, production engineers and maintenance managers. The book will serve as a consolidated volume on various dimensions of machine tool reliability and its implications from manufacturers and users point of view. From the manufacturers' point of view, it discusses various approaches for reliability and maintenance based design of machine tools. In specific, it discusses simultaneous selection of optimal reliability configuration and maintenance schedules, maintenance optimization under various maintenance scenarios and cost based FMEA. From the users' point of view, it explores the role of machine tool reliability in shop floor level decision- making. In specific, it shows how to model the interactions of machine tool reliability with production scheduling, maintenance scheduling and process quality control. © 2016 Scrivener Publishing LLC. All rights reserved.

Machine Tool Reliability

Performance of a production system depends on breakdown-free operation of equipment and processes. Maintenance and quality control play an important role in achieving this goal. This paper presents an integrated model for joint optimization of preventive maintenance and quality control policy with cumulative sum (CUSUM) control chart parameters. Two types of maintenance policies are considered, namely minimal corrective maintenance and imperfect preventive maintenance. The proposed model enables the determination of the optimal value of each of the five decision variables, i.e. sample size (n), sample interval (h), the reference value (K), the decision interval (h1) and preventive maintenance interval (tPM), that minimize the expected total system cost per unit time. A numerical example is presented to demonstrate the effect of the cost parameters on the integrated design of preventive maintenance and quality control policy. It also compares the system performance employing the proposed integrated approach with that obtained by considering maintenance and CUSUM chart independently. Substantial economic benefit of 19 \% is seen in the joint optimization. © 2015, Springer-Verlag London.