Real-time Production Scheduling Research Articles

Construction of a Digital Twin System and Dynamic Scheduling Simulation Analysis of a Flexible Assembly Workshops with Island Layout

Assembly Workshops with Island Layout (AWIL) possess flexible production capabilities that realize product diversification. To cope with the complex scheduling challenges in flexible workshops, improve resource utilization, reduce waste, and enhance production efficiency, this paper proposes a production scheduling method for flexible assembly workshops with an island layout based on digital twin technology. A digital twin model of the workshop is established according to production demands to simulate scheduling operations and deal with complex scheduling issues. A workshop monitoring system is developed to quickly identify abnormal events. By employing an event-driven rolling-window rescheduling technique, a dynamic scheduling service system is constructed. The rolling window decomposes scheduling problems into consecutive static scheduling intervals based on abnormal events, and a genetic algorithm is used to optimize each interval in real time. This approach provides accurate, real-time scheduling decisions to manage disturbances in workshop production, which can enhance flexibility in the production process, and allows rapid adjustments to production plans. Therefore, the digital twin system improves the sustainability of the production system, which will provide a theoretical research foundation for the real-time and unmanned production scheduling process, thereby achieving sustainable development of production.

Real-Time Production Scheduling and Industrial Sonar and Their Application in Autonomous Mobile Robots

In real-time production planning, there are exceptional events that can cause problems and deviations in the production schedule. These circumstances can be solved with real-time production planning, which is able to quickly reschedule the operations at each work centre. Mobile autonomous robots are a key element in this real-time planning and are a fundamental link between production centres. Work centres in Industry 4.0 environments can use current technology, i.e., a biomimetic strategy that emulates echolocation, with the aim of establishing bidirectional communication with other work centres through the application of agile algorithms. Taking advantage of these communication capabilities, the basic idea is to distribute the execution of the algorithm among different work centres that interact like a parasympathetic system that makes automatic movements to reorder the production schedule. The aim is to use algorithms with an optimal solution based on the simplicity of the task distribution, trying to avoid heuristic algorithms or heavy computations. This paper presents the following result: the development of an Industrial Sonar algorithm which allows real-time scheduling and obtains the optimal solution at all times. The objective of this is to reduce the makespan, reduce energy costs and carbon footprint, and reduce the waiting and transport times for autonomous mobile robots using the Internet of Things, cloud computing and machine learning technologies to emulate echolocation.

Real-time production scheduling using a deep reinforcement learning-based multi-agent approach

In the real-time scheduling (RTS) research field, it has been shown that employing multiple dispatching rules (MDRs) for the components in a flexible manufacturing system will improve production performance much more than a single dispatching rule (SDR). To fulfill the goal of Industry 4.0 in production control and improve production performance, this study deploys a deep reinforcement learning-based multi-agent (DRLBMA) approach for real-time scheduling. The proposed approach uses the MDRs strategy by integrating two main methodologies: an off-line learning module and a Deep Q-learning-based multi-agent module. The proposed method employs a two-level self-organizing map (SOM) to determine the system’s states. The proposed methodology determines the best MDRs decision. The approach is applied to a case study of a smart manufacturing system. The results of the proposed method are compared to different scheduling strategies, such as reinforcement learning (RL)-based real-time scheduling, two-level self-organized map (SOM), and continuous rescheduling using a single dispatching rule, such as earliest due date (EDD), shortest processing time (SPT), and longest processing time (LPT). The findings reveal that, in terms of the total weighted tardiness, throughput, and mean cycle time performance criteria, the proposed DRLBMA-based real-time scheduling is more efficient than these scheduling strategies.

A real-time production scheduling method for RFID-enabled semiconductor back-end shopfloor environment in industry 4.0

PurposeA real-time production scheduling method for semiconductor back-end manufacturing process becomes increasingly important in industry 4.0. Semiconductor back-end manufacturing process is always accompanied by order splitting and merging; besides, in each stage of the process, there are always multiple machine groups that have different production capabilities and capacities. This paper studies a multi-agent based scheduling architecture for the radio frequency identification (RFID)-enabled semiconductor back-end shopfloor, which integrates not only manufacturing resources but also human factors.Design/methodology/approachThe architecture includes a task management (TM) agent, a staff instruction (SI) agent, a task scheduling (TS) agent, an information management center (IMC), machine group (MG) agent and a production monitoring (PM) agent. Then, based on the architecture, the authors developed a scheduling method consisting of capability & capacity planning and machine configuration modules in the TS agent.FindingsThe authors used greedy policy to assign each order to the appropriate machine groups based on the real-time utilization ration of each MG in the capability & capacity (C&C) planning module, and used a partial swarm optimization (PSO) algorithm to schedule each splitting job to the identified machine based on the C&C planning results. At last, we conducted a case study to demonstrate the proposed multi-agent based real-time production scheduling models and methods.Originality/valueThis paper proposes a multi-agent based real-time scheduling framework for semiconductor back-end industry. A C&C planning and a machine configuration algorithm are developed, respectively. The paper provides a feasible solution for semiconductor back-end manufacturing process to realize real-time scheduling.

A deep multi-agent reinforcement learning approach to solve dynamic job shop scheduling problem

Manufacturing industry is experiencing a revolution in the creation and utilization of data, the abundance of industrial data creates a need for data-driven techniques to implement real-time production scheduling. However, existing dynamic scheduling techniques have been mainly developed to solve problems of invariable size, and are incapable of addressing the increasing volatility and complexity of practical production scheduling problems. To facilitate near real-time decision-making on the shop floor, we propose a deep multi-agent reinforcement learning-based approach to solve the dynamic job shop scheduling problem. Double deep Q-network algorithm, attached to decentralized scheduling agents, is used to learn the relationships between production information and scheduling objectives, and to make near real-time scheduling decisions. Proposed framework utilizes centralized training and decentralized execution scheme and parameter-sharing technique to tackle the non-stationary problem in the multi-agent reinforcement learning task. Several enhancements are also developed, including the novel state and action representation that can handle size-agnostic dynamic scheduling problems, a chronological joint-action framework to alleviate the credit-assignment difficulty, and knowledge-based reward-shaping techniques to encourage cooperation. Simulation study shows that the proposed architecture significantly improves the learning effectiveness, and delivers superior performance compared to existing scheduling strategies and state-of-the-art deep reinforcement learning-based dynamic scheduling approaches.

Research on a Real-time Job-shop Scheduling Method Based on Reinforcement Learning

At present, manufacturing models are characterized by multi-variety, small batch, and diversification. It is insufficient to use traditional scheduling methods for production management with high performance. A real-time production scheduling system based on reinforcement learning (RL) is suggested in an effort to address the aforementioned issues. A brand-new manufacturing neural network is created to learn the state-action values for production scheduling in real time using high-dimensional data as the input. The detailed setup of network inputs, neural network, action, and reward are also designed. Then, a policy-based reinforcement learning algorithm is proposed to achieve the optimum objective. Finally, By contrasting the proposed scheduling strategy with rule-based approaches in a smart manufacturing environment, its efficacy is demonstrated. according to experimental data, the suggested algorithm can successfully improve performance in the dynamic job-shop environment.

Multi-Agent Reinforcement Learning for Real-Time Dynamic Production Scheduling in a Robot Assembly Cell

As industry rapidly shifts towards mass personalisation, the need for a decentralised multi-agent system capable of dynamic flexible job shop scheduling (FJSP) is evident. Traditional heuristic and meta-heuristic scheduling methods cannot achieve satisfactory results and have limited application to static environments. Recent Reinforcement Learning (RL) approaches that consider dynamic FJSP, lack flexibility and autonomy as they use a single-agent centralised model, assuming global observability. As such, we propose a Multi-Agent Reinforcement Learning (MARL) system for scheduling dynamically arriving assembly jobs in a robot assembly cell. We applied a Double DQN-based algorithm and proposed a generalised observation, action and reward design for the dynamic FJSP setting. Using a centralised training phase, each agent (i.e., robot) in the assembly cell executes decentralised scheduling decisions based on local observations. Our solution demonstrated improved performance against rule-based heuristic methods, for optimising makespan. We also reported the impact of different observation sizes of each agent on optimisation performance.

Network-based dynamic dispatching rule generation mechanism for real-time production scheduling problems with dynamic job arrivals

Although the concept of Industrial 4.0 has been well accepted, only few studies have dealt with real-time production scheduling of smart factories. Due to the advantages of simplicity, efficiency and quick response, heuristic rules have become the most promising technology to solve such problems. However, they suffer some drawbacks, such as high development and maintenance costs, low solution quality, and excessive emphasis on local information. To design heuristics from the perspective of system optimization and ensure the performance of heuristics in real-time production scheduling environments, this study develops a network-based dynamic dispatching rule generation mechanism. The complex network theory is introduced to extract a series of low-level heuristics from the perspective of system optimization, while the automatic heuristic generation problem is formulated as a multiple attribute decision making problem. Given that the dispersity of local features indicates their value for decision-making, the entropy weighting method is employed to automatically produce an adequate combination of the provided easy-to-implement low-level heuristics. Finally, the open shop scheduling problem with dynamic job arrivals is taken as an example to evaluate the effectiveness of the proposed algorithm. Numerical results demonstrate the excellent performance of the proposed algorithm in terms of algorithm effectiveness and computational time.

CPS-enabled and knowledge-aided demand response strategy for sustainable manufacturing

The utilization of advanced industrial informatics, such as industrial internet of things and cyber-physical system (CPS), provides enhanced situation awareness and resource controllability, which are essential for flexible real-time production scheduling and control (SC). Regardless of the belief that applying these advanced technologies under electricity demand response can help alleviate electricity demand–supply mismatches and eventually improve manufacturing sustainability, significant barriers have to be overcome first. Particularly, most existing real-time SC strategies remain limited to short-term scheduling and are unsuitable for finding the optimal schedule under demand response scheme, where a long-term production scheduling is often required to determine the energy consumption shift from peak to off-peak hours. Moreover, SC strategies ensuring the desired production throughput under dynamic electricity pricing and uncertainties in manufacturing environment are largely lacking. In this research, a knowledge-aided real-time demand response strategy for CPS-enabled manufacturing systems is proposed to address the above challenges. A knowledge-aided analytical model is first applied to generate a long-term production schedule to aid the real-time control under demand response. In addition, a real-time optimization model is developed to reduce electricity costs for CPS-enabled manufacturing systems under uncertainties. The effectiveness of the proposed strategy is validated through the case study on a steel powder manufacturing system. The results indicate the exceptional performance of the proposed strategy as compared to other real-time SC strategies, leading to a reduction of electricity cost up to 35.6% without sacrificing the production throughput.

Deep Reinforcement Learning-Based Job Shop Scheduling of燬mart燤anufacturing

Industry 4.0 production environments and smart manufacturing systems integrate both the physical and decision-making aspects of manufacturing operations into autonomous and decentralized systems. One of the key aspects of these systems is a production planning, specifically, Scheduling operations on the machines. To cope with this problem, this paper proposed a Deep Reinforcement Learning with an Actor-Critic algorithm (DRLAC). We model the Job-Shop Scheduling Problem (JSSP) as a Markov Decision Process (MDP), represent the state of a JSSP as simple Graph Isomorphism Networks (GIN) to extract nodes features during scheduling, and derive the policy of optimal scheduling which guides the included node features to the best next action of schedule. In addition, we adopt the Actor-Critic (AC) network’s training algorithm-based reinforcement learning for achieving the optimal policy of the scheduling. To prove the proposed model’s effectiveness, first, we will present a case study that illustrated a conflict between two job scheduling, secondly, we will apply the proposed model to a known benchmark dataset and compare the results with the traditional scheduling methods and trending approaches. The numerical results indicate that the proposed model can be adaptive with real-time production scheduling, where the average percentage deviation (APD) of our model achieved values between 0.009 and 0.21 compared with heuristic methods and values between 0.014 and 0.18 compared with other trending approaches.

A hybrid multi-objective approach for real-time flexible production scheduling and rescheduling under dynamic environment in Industry 4.0 context

With the advent of industry-4.0 era, industrial production are evolving towards high flexibility, diversity, customisation, and dynamism. We address a realistic scenario of a smart manufacturing system, which concerns the production scheduling of complex multi-level products under a dynamic flexible job shop environment with shop floor disruptions incorporated. The products are assembled from multiple basic parts, whose fabrication processes are highly flexible, involving alternative process plans, alternative machines and alternative processing sequences of operations. We aim at providing Pareto solutions, with consideration of three typical optimisation objectives, including makespan, maximum machine workload, and total tardiness. A hybrid MPGA-CP approach is designed for the problem. To the best our knowledge, this is the first attempt to embed an exact optimisation technique into a meta-heuristic algorithm in the domain of production scheduling. Compared with other alternative approaches, its efficiency and performance are proven to be outstanding in solving medium-to-large scale problems, covering the largest proportion of Pareto solutions among all tested approaches. Furthermore, we constructed a simulation model of a real-time production scheduling control system, in which our approach is embedded as the kernel algorithm, to study the impacts of some uncertainties that are concerned in practice. Based on the results of simulation experiments and sensitivity analysis, meaningful managerial insights have been provided.

Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning

Job-shop scheduling problem (JSP) is used to determine the processing order of the jobs and is a typical scheduling problem in smart manufacturing. Considering the dynamics and the uncertainties such as machine breakdown and job rework of the job-shop environment, it is essential to flexibly adjust the scheduling strategy according to the current state. Traditional methods can only obtain the optimal solution at the current time and need to rework if the state changes, which leads to high time complexity. To address the issue, this paper proposes a dynamic scheduling method based on deep reinforcement learning (DRL). In the proposed method, we adopt the proximal policy optimization (PPO) to find the optimal policy of the scheduling to deal with the dimension disaster of the state and action space caused by the increase of the problem scale. Compared with the traditional scheduling methods, the experimental results show that the proposed method can not only obtain comparative results but also can realize adaptive and real-time production scheduling.

Realtime production scheduling and control systems in smart industry

For a production system, 'scheduling' aims to find out which machine/worker processes which job at what time to produce the best result for user-set objectives, such as minimising the total cost. Finding the optimal solution to a large scheduling problem, however, is extremely time consuming due to the high complexity. To reduce this time to one instance, Dr Wei Weng, from the Institute of Liberal Arts and Science, Kanazawa University in Japan, is leading research projects on developing online scheduling and control systems that provide near-optimal solutions in real time, even for large production systems. In her system, a large scheduling problem will be solved as distributed small problems and information of jobs and machines is collected online to provide results instantly. This will bring two big changes: 1. Large scheduling problems, for which it tends to take days to reach the optimal solution, will be solved instantly by reaching near-optimal solutions; 2. Rescheduling, which is still difficult to be made in real time by optimization algorithms, will be completed instantly in case some urgent jobs arrive or some scheduled jobs need to be changed or cancelled during production. The projects have great potential in raising efficiency of scheduling and production control in future smart industry and enabling achieving lower costs, higher productivity and better customer service.

Graduation Intelligent Manufacturing System (GiMS): an Industry 4.0 paradigm for production and operations management

PurposeThe purpose of this paper is to develop an intelligent manufacturing system for transforming production management and operations to an Industry 4.0 manufacturing paradigm.Design/methodology/approachA manufacturing mode-Graduation Manufacturing System is designed for organizing and controlling production operations. An Industrial Internet of Things (IIoT) and digital twin-enabled Graduation Intelligent Manufacturing System (GiMS) with real-time task allocation and execution mechanisms is proposed to achieve real-time information sharing and production planning, scheduling, execution and control with reduced complexity and uncertainty.FindingsThe implementation of GiMS in an industrial company illustrates the potential advantages for real-time production planning, scheduling, execution and control with reduced complexity and uncertainty. For production managers and onsite operators, effective tools, such as cloud services integrates effective production and operations management strategies are needed to facilitate their decision-making and daily operations at the operational level.Originality/valueThis paper presents an Industry 4.0 paradigm-GiMS, which aims to explore Industry 4.0 technologies opportunities on operations and production management, especially on production planning, scheduling, execution and control.

Product Completion Time Prediction Using A Hybrid Approach Combining Deep Learning and System Model

The prediction of product completion time is critical in real time production scheduling and control to achieve customer demand satisfaction. However, it is a challenging task due to the increasing complexity of production systems and greater diversity of products. The recent advancement in data-driven approach and machine learning algorithms have provided unprecedent opportunities to tackle such problems that otherwise very difficult to solve using conventional methods in the manufacturing industry. However, most existing studies on product completion time prediction adopt a purely data-driven approach while ignoring the prospect of integrating domain knowledge in their machine learning models. In this paper, we propose a hybrid approach to predicting product completion time by combining the strengths of both machine learning techniques and analytical system model. A mathematical model for multi-product serial production line is proposed to describe the real-time dynamics of the system. With this model, the strict lower bound of product completion time can be efficiently computed for given system status, where the lower bound represents the least possible product completion time when assuming no random downtime in the system. Instead of directly predicting the product completion time, a deep learning model is developed to only predict the distance between the lower bound and actual product completion time. Guided by properties of production system, we discover a recurrent sequence in the prediction problem by modeling each machine and product as recurrent units. The Long Short-Term Memory (LSTM) method, a prominent variant of recurrent neural network (RNN), is used to combine with the system model to predict the product completion time in a real-time fashion.

Real-Time Production and Logistics Self-Adaption Scheduling Based on Information Entropy Theory.

In recent years, the individualized demand of customers brings small batches and diversification of orders towards enterprises. The application of enabling technologies in the factory, such as the industrial Internet of things (IIoT) and cloud manufacturing (CMfg), enhances the ability of customer requirement automatic elicitation and the manufacturing process control. The job shop scheduling problem with a random job arrival time dramatically increases the difficulty in process management. Thus, how to collaboratively schedule the production and logistics resources in the shop floor is very challenging, and it has a fundamental and practical significance of achieving the competitiveness for an enterprise. To address this issue, the real-time model of production and logistics resources is built firstly. Then, the task entropy model is built based on the task information. Finally, the real-time self-adaption collaboration of production and logistics resources is realized. The proposed algorithm is carried out based on a practical case to evaluate its effectiveness. Experimental results show that our proposed algorithm outperforms three existing algorithms.

Real-time production scheduling in the Industry-4.0 context: Addressing uncertainties in job arrivals and machine breakdowns

The utilization of real-time information in production scheduling decisions becomes possible with the help of new developments in Information Technology and Industrial Informatics, such as Industry 4.0. Regardless of the beliefs that the availability of such information will enhance scheduling decisions, several questions and concerns have been reported. One such question is to what extent can the availability of real-time information enhance scheduling decisions? Another concern is how can such information be utilized to advance scheduling decisions and when should it be used? Moreover, there is a general assumption that continuous rescheduling using real-time system updates is beneficial to some extent. However, this general assumption has not been extensively investigated in complex manufacturing systems, such as flexible job shops. Therefore, in this paper, our objective is to study the above-mentioned research questions by developing real-time scheduling (RTS) models for the flexible job-shop scheduling problem (FJSP) with unexpected new job arrivals and machine random breakdowns. We investigate how real-time updates on unexpected arrivals, the availability of machines (downtimes and recovery times), and the completion times of operations can be utilized to generate new schedules (i.e., rescheduling). The performance of the developed RTS models is also investigated under different settings for shop-floor events, different rescheduling strategies, rescheduling policies, and scheduling methods. Lastly, results, conclusions, and several promising research avenues are provided.

Spatial-Temporal Finite Element Analytics for Cyber-Physical System-enabled Smart Factory: Application in Hybrid Flow Shop

Cyber-Physical System (CPS) is a crucial direction in realizing the next-generation smart manufacturing. With the deployment of IoT technologies, massive production data and information are real-timely accessible for decision-makers. However, the enemies: complexity and uncertainty, that researchers and practitioners have been fighting for decades still hinder the development of smart manufacturing. In the realm of manufacturing optimization like production planning and scheduling, considerable research efforts have been made. However, more or less similar results are generated, which are theoretically optimal but lack the ability to cope with disturbances in the real-life industry. This study develops a framework of the Cyber-Physical System (CPS) and proposes a smart digitalization solution to achieve real-time visibility, traceability, and information sharing. Also, a novel Spatial-Temporal Finite Element Analytics (ST-FEA) based on real-time cyber-physical visibility and traceability is innovated to achieve real-time advanced production planning and scheduling in the Hybrid Flow Shop. By discretizing the space and time of the original problem in meshing, the complexity and uncertainty are substantially reduced. The simpler models can thus be established and solved with a more straightforward method. Case studies will be conducted to verify the practicability and effectiveness of the proposed method in future research.

The ‘Internet of Things’ enabled real-time scheduling for remanufacturing of automobile engines

Abstract Typical challenges that managers of remanufacturing face are composed of the lack of timely, accurate, and consistent information of remanufacturing resources. Therefore, it is difficult to implement real-time production scheduling for the shop floor. To address this problem, the authors applied the concept of the ‘Internet of Things’ to the remanufacturing of automobile engines to form an Internet of Manufacturing Things environment. Under the Internet of Manufacturing Things, an identification technology for disassembled engine parts was designed, and the real-time status of the remanufacturable resources can be monitored. Based on the captured remanufacturing information, a real-time production scheduling method was developed, and a mathematical model was developed to achieve cost reduction, dynamic management of remanufacturable resources, and energy consumption decrease. To obtain an optimal solution, a Pareto-based optimization method was used. Finally, a case study was performed to analyze the effectivity of the proposed method. The results showed that the remanufacturing cost and energy consumption were reduced by 34% and 34% respectively, and the worker load rate was more balanced. These improvements can contribute to more sustainable development and greener production within the remanufacturing industry, especially for remanufacturing of automobile engines.

Integrated real-time production scheduling of a multiple cryogenic air separation unit and compressor plant

The development and application of an integrated real-time production scheduling and control strategy for a multiple cryogenic air separation unit (ASU) and compressor plant is discussed. Using a top-down optimisation approach, the operational targets for ASU production and compressor configuration are obtained for a given customer demand and subsequently managed using a real-time optimisation strategy. This is integrated with existing control to implement the steady-state configuration targets subject to process disturbances, power price fluctuations and against network change penalty weightings. Network material balance and network component operating constraints are met while simultaneously minimising plant reconfiguration costs during transient operation which occurs as a result of changing demands. Implemented using mixed integer linear programming, it is demonstrated that the two-stage optimisation strategy improves site operating costs by an average of 5% over the considered trial period (which would translate into substantial cost savings for such an energy intensive process).