Robust Assembly Assistance Using Informed Tree Search with Markov Chains
Manual work accounts for one of the largest workgroups in the European manufacturing sector, and improving the training capacity, quality, and speed brings significant competitive benefits to companies. In this context, this paper presents an informed tree search on top of a Markov chain that suggests possible next assembly steps as a key component of an innovative assembly training station for manual operations. The goal of the next step suggestions is to provide support to inexperienced workers or to assist experienced workers by providing choices for the next assembly step in an automated manner without the involvement of a human trainer on site. Data stemming from 179 experiment partici…
Assembly Assistance System with Decision Trees and Ensemble Learning
This paper presents different prediction methods based on decision tree and ensemble learning to suggest possible next assembly steps. The predictor is designed to be a component of a sensor-based assembly assistance system whose goal is to provide support via adaptive instructions, considering the assembly progress and, in the future, the estimation of user emotions during training. The assembly assistance station supports inexperienced manufacturing workers, but it can be useful in assisting experienced workers, too. The proposed predictors are evaluated on the data collected in experiments involving both trainees and manufacturing workers, as well as on a mixed dataset, and are compared …
Human-centred Assembly: A Case Study for an Anthropocentric Cyber-physical System
Abstract To engineer the factory of the future the paper argues for an anthropocentric cyber-physical reference model that assimilate in an integrated, dynamic, structural and functional way all the required components (i.e. physical, computational and human) of a synthetic hybrid system. This is due to the real need to design large-scale complex systems that accommodate the latest achievements in factory automation where the human is not merely playing a simple and clear role inside the control-loop, but is becoming a composite factor in a highly automated system (“man-in-the-mesh”). The concept is demonstrated by instantiating our anthropocentric cyber-physical reference model in a concre…
Conceptual Overview of an Anthropocentric Training Station for Manual Operations in Production
Abstract The paper presents a conceptual overview of a human-centred training station for manual operations (ATASMO). It identifies the main users of the system but also the long-tern targeted features of ATASMO. Moreover, the current implementation, its limitations and future work on ATASMO is synthetically presented.
Do Not Cancel My Race with Cyber-Physical Systems
Abstract To engineer the factory of the future the paper argues for a reference model that is not necessary restricted to the control component, but integrates the physical and human components as well. This is due to the real need to accommodate the latest achievements in factory automation where the human is not merely playing a simple and clear role inside the control-loop, but is becoming a composite factor in a highly automated system (“man in the mesh”). The concept is demonstrated by instantiating the anthropocentric cyber-physical reference architecture for smart factories (ACPA4SF) in a concrete case study that needs to accommodate the ongoing researches from the SmartFactory KL fa…
Real-Time Assembly Support System with Hidden Markov Model and Hybrid Extensions
This paper presents a context-aware adaptive assembly assistance system meant to support factory workers by embedding predictive capabilities. The research is focused on the predictor which suggests the next assembly step. Hidden Markov models are analyzed for this purpose. Several prediction methods have been previously evaluated and the prediction by partial matching, which was the most efficient, is considered in this work as a component of a hybrid model together with an optimally configured hidden Markov model. The experimental results show that the hidden Markov model is a viable choice to predict the next assembly step, whereas the hybrid predictor is even better, outperforming in so…
Engineering insights from an anthropocentric cyber-physical system: A case study for an assembly station
Abstract To effectively cope with the complexity of manufacturing control problems the cyber-physical systems are engineered to work in the social space. Therefore the research in the field of cyber-physical systems needs to address social aspects when this concept is adopted in factory automation. The paper argues for an anthropocentric cyber-physical reference model as the basic decomposition unit for the design of distributed manufacturing control systems. The model assimilates all the required components (i.e. physical, computational and human) of a synthetic hybrid system in an integrated way. This is due to the real need to design cyber-physical production systems where the technologi…
Smart factory in the context of 4th industrial revolution: challenges and opportunities for Romania
Manufacturing companies, independent of operation sector and size, must be able to produce lot size one products, just-in-time at a competitive cost. Coping with this high adaptability and short reaction times proves to be very challenging. New approaches must be taken into consideration for designing modular, intelligent and cooperative production systems which are easy to integrate with the entire factory. The coined term for this network of intelligent interacting artefacts system is cyber-physical systems (CPS). CPS is often used in the context of Industry 4.0 – or what many consider the forth industrial revolution. The paper presents an overview of key technological and social requirem…
Prediction-Based Assembly Assistance System
This paper presents the design of a prediction-based assembly assistance system for manual operations and the results obtained on the data collected from experiments of assembling a customizable product. We integrated into the proposed system a Markov predictor improved with a padding mechanism whose role is to recommend the next assembly step and to detect the worker’s errors. The predictor is trained with correct assembly patterns and tested with real assembly/manufacturing data. The proposed predictor improves the coverage and, thus, there is a significantly higher number of assembly steps which are correctly correlated with the real intentions of the workers.
Interaction Mechanism of Humans in a Cyber-Physical Environment
The research initiative “Industrie 4.0” (I4.0) of the high-tech strategy announced by the German government targets the deployment of a cyber-physical system (CPS) in production and logistics. Such CPS-based environments are characterized by an increasing number of heterogeneous intelligent autonomous and communicating artifacts tightly integrated with humans. Thus, the human’s role will become a composite factor (“man-in-the-mesh”) for this future CPS environment, playing more than just a simple role inside the control loop. This paper investigates the need of a robust communication between CPS and humans, which includes a clear semantic of the exchanged information. For this purpose, a me…