Sustainable cybernetic manufacturing

Cybernetic manufacturing aims for flexible and adaptive manufacturing operations locally or globally by using integrated technologies that can combine the advanced computing power with manufacturing equipment. In recent years, research on Cyber-Physical Systems (CPS), Internet of Things (IoT), and Big Data has been active in such areas like transportation, smart home, robotic surgery, aviation, defence, critical infrastructure, etc. The advancements in CPS, IoT, and Big Data also affected manufacturing positively in the form of Cyber-Physical Production Systems, Industrial Internet of Things, and Big Manufacturing Data Analytics. The ambition is to largely enhance manufacturing automation and control through machine-embedded intelligence. Moreover, the advancements in Web-, Internet-, and Cloud-based systems and applications have opened up the possibility for industries to utilise the cyber workspace to conduct efficient and effective daily operations from anywhere around the clock, e.g. in cloud manufacturing environments. On the other hand, manufacturing sustainability and related directives have become unavoidable issues that future factories must address. Research works, in particular in the context of Industry 4.0 and Industrial Internet, are emerging. Altogether they contribute to the realisation of Sustainable Cybernetic Manufacturing. It leads to the need for publishing a collection of research papers in this promising area, as a Special Issue of the International Journal of Production Research. After rigorous reviews of multiple rounds, 15 papers have been accepted for inclusion in this special issue. Their brief synopses are provided below.

The first paper titled ‘Industry 4.0: Smart Scheduling’ introduces a new decision-making schema, intended to yield flexible and efficient production schedules on the fly, taking advantage of the features of smart manufacturing and Industry 4.0 production environments. The ability to face unforeseen and disruptive events is one of the main improvements in the proposed schema, which uses an efficient screening procedure (Tolerance Scheduling) to lessen the need of rescheduling in the face of those events. The second paper titled ‘Service-Oriented Robust Parallel Machine Scheduling’ continues the scheduling topic and further investigates a stochastic parallel machine scheduling problem, assuming that only the mean and covariance matrix of the processing times are known, due to the lack of historical data. The objective is to maximise the service level, which measures the probability of all jobs jointly completed before or at their due dates. The reported results show that their approach can obtain higher solution quality with less computational effect. As the title suggested, the third paper on ‘Auction-based Cooperation Mechanism for Cell Part Scheduling with Transportation Capacity Constraint’ addresses the cell part scheduling problem, aiming to minimise the overall make-span under the constraint of transportation capacity. An auction-based heuristic approach is proposed to solve the problem, which focuses on dealing with cooperation between machines and automated guided vehicles. A new improved disjunctive graph model is developed to optimise the feasible solutions obtained by the auction-based approach. The fourth paper titled ‘Multi-Objective Optimization of Multi-Task Scheduling in Cloud Manufacturing’ proposes a comprehensive model for scheduling multiple distinct tasks with complicated manufacturing processes in a cloud manufacturing environment. Two multi-objective meta-heuristic algorithms, i.e. ACO and NSGA-II, are designed to solve the scheduling problem. Experimental results indicate that in most cases ACO can obtain a more diverse set of Pareto solutions hence offering more alternatives to meet widely different users’ needs. The fifth paper titled ‘Drum Buffer Rope Based Heuristic for Multi-Level Rolling Horizon Planning in Mixed Model Production’ proposes a drum buffer rope-based heuristic algorithm for multi-level planning, considering shifting bottleneck resource to make an efficient schedule in the rolling horizon in a mixed model production environment while utilising capacity constraint resource at maximum. Results indicate that the proposed method is significant for reducing the gap between medium-level planning and lower-level schedules and gives an efficient medium-level plan and lower-level schedule in each planning horizon as compared to other methods. The proposed method is claimed to be useful to implement Industry 4.0 in mixed model industries and update their plan and schedule in real time.

The sixth paper titled ‘Digital Twin-based WEEE Recycling, Recovery and Remanufacturing in the Background of Industry 4.0’ introduces two enablers of digital twin and Industry 4.0 to the WEEE (waste electrical and electronic equipment) remanufacturing industry. The goal is to provide an integrated and reliable cyber-avatar of the individual WEEE, thus forming a personalised service system. The feasibility of the proposed system and methodologies is validated and evaluated during implementations in a cloud and cyber-physical system. The seventh paper presents a methodology on ‘Digital Twin-Driven Rapid Individualized Designing of Automated Flow-Shop Manufacturing System’, aiming to provide engineering solution analysis capabilities and generate an authoritative digital design of the system at pre-production phase. A bi-level iterative coordination mechanism is proposed to achieve optimal design performance for the required functions. A case study is included to prove the feasibility and effectiveness of the proposed methodology. The eighth paper titled ‘Digital Twin for Rotating Machinery Fault Diagnosis in Smart Manufacturing’ reports a Digital Twin reference model for rotating machinery fault diagnosis. A model updating scheme based on parameter sensitivity analysis is proposed to enhance the model adaptability. Experimental data are collected from a rotor system that emulates an unbalance fault and its progression. The data are then input to a Digital Twin model of the rotor system to investigate its ability to unbalance quantification and localisation for fault diagnosis. The results show that the constructed Digital Twin rotor model enables accurate diagnosis and adaptive degradation analysis. The ninth paper titled ‘Digital Twin Driven Product Design Framework’ presents a new method for product design based on the digital twin approach. The development of product design is briefly introduced. A framework of digital twin-driven product design (DTPD) is then proposed and analysed. A use case is presented to illustrate the application of the proposed DTPD method.

The tenth paper titled ‘Feature-based Function Block Control Framework for Manufacturing Equipment in Cloud Environments’ introduces a cloud service-based control approach which is built on the combination of event-driven IEC 61,499 Function Blocks and the manufacturing features of products. Distributed control is realised through the use of a networked control structure of such Function Blocks as decision modules, enabling an adaptive runtime behaviour. An application scenario is presented to demonstrate the applicability of the control approach. The eleventh paper focuses on an ‘IoT-enabled Cloud-based Additive Manufacturing Platform to Support Rapid Product Development’. Internet of Things (IoT) provides new capabilities to the cloud platform, enabling customers to control and monitor the printing process remotely. The authors of this paper also examined the feasibility of Artificial Neural Networks for surface defect detection. This platform is able to work in dynamic and iterative product development processes and reduce development time and cost. An illustrative platform is developed to demonstrate the functionalities. The twelfth paper titled ‘Predictive Modeling of Surface Roughness in Fused Deposition Modeling Using Data Fusion’ presents a data fusion approach to predicting surface roughness in fused deposition modelling (FDM) processes. The predictive models are trained using random forests, support vector regression, ridge regression, and least absolute shrinkage and selection operator. A real-time monitoring system is developed to monitor the health condition of an FDM machine in real-time using multiple sensors. Experimental results show that the predictive models trained using machine learning algorithms are capable of predicting the surface roughness of additively manufacturing parts with high accuracy. The thirteenth paper titled ‘Logistics-Aware Manufacturing Service Collaboration Optimization towards Industrial Internet Platform’ proposes an adjacent matrix-based logistics-aware manufacturing service collaboration optimisation (LA-MSCO) model with detailed definitions of time, cost and reliability attributes of logistics. An improved artificial bee colony algorithm with both dimensional self-adaptation and group leader mechanisms, i.e. DSA-GL-ABC, is proposed for solving the LA-MSCO problem. Simulation experiments revealed the better performance of DSA-GL-ABC algorithm in terms of searching capability, convergence speed and solution quality. The fourteenth paper titled ‘Human-Robot Collaboration in Disassembly for Sustainable Manufacturing’ addresses issues in sustainability through human-robot collaborative disassembly (HRCD). Deep reinforcement learning, incremental learning and transfer learning are also investigated for HRCD. The demonstration in the case study contains experimental results of multi-modal perception for robot system and the human body in a hybrid human–robot collaborative disassembly cell, sequence planning for an HRCD task, distance-based safety strategy and motion-driven control method. It shows high feasibility and effectiveness of the proposed approaches for HRCD and verifies the functionalities of the framework. The fifteenth paper presents ‘Sustainable and Flexible Industrial Human Machine Interfaces to Support Adaptable Applications in the Industry 4.0 Paradigm’. This work includes functional hardware and novel software architecture to build flexible advanced human-machine interfaces that can provide adaptable and useful information to the operators of machines. Industrial protocols are used to receive real-time data. Three use cases, customised for 3D printers, real-time motor control and a digital twin of a robotic arm receiving real-time data from the actual robotic arm, are reported to validate the interfaces.

Finally, we wish to take this opportunity to thank all the authors for their scientific contributions to the special issue, and for complying with referees’ comments in revising their manuscripts. Through this special issue, we would like to shed some light on the latest advancements in sustainable cybernetic manufacturing research along with the remaining challenges and hope to open doors for new research ideas and achievements in the years to come.