Ph. D. Project
Title:
Human integration to manufacturing control system : human factors, socio-cultural inspired interactions
Dates:
2021/10/01 - 2024/09/30
Description:
The changing nature of industrial requirements brings with it extensive new studies in manufacturing systems
where reactivity in the short term and adaptability to market changes in the long term become increasingly
demanded. To cover these new requirements, some efforts in manufacturing control have been paid to
propose hybrid control architecture and methodologies, where distributed artificial intelligence plays an
essential role (Cardin et al., 2017). For this purpose, the industry for the future paradigm brings technological
advancement due to Information and Communication Technologies (ICT), as well as to advancement in
distributed computer sciences. The advancement from Industry 4.0 aims to face the evolution of customer
needs, in terms of reactivity and performances. However, in spite of technological evolution, the
implementation of hybrid control in industry remains a complex challenge. This complexity is mainly due to the
human, which, in one hand, is excluded in the design of control methodologies, and in the other hand, does
not accept the technology (Bril El-Haouzi, 2017).

This thesis aims to propose a new design approach of manufacturing control, which consider the human in the
system. This approach, called "anthropocentric", is based on the assumption, proved by several researches in
anthropology ( ), that human better accepts the technology within its environment, if this technology
behaves and communicates similarly as him. These researches on anthropocentric approaches have started on
two previous thesis frameworks. The first one focused on the design of human-inspired control algorithms
such as negotiation or consensus (Mezgebe et al., 2019). The second one focused on the social relationships,
where a meta-model have been proposed. This meta-model leads to a new paradigm, called "Internet of Social
Agents (IoSA)", where each entity (i.e. agent) of the network can be an object (IoT) or a human (Valette et al,
2020).

The originality of the proposed thesis is the design of manufacturing control, by considering both the human
factors and the social aspect from IoSA paradigm. The first phase of the design leads the modeling of an agent
(state, dynamic, decisions), which will integrate both human (e.g. physical and mental conditions) and social
(interaction with others) dimensions. For applicability purpose, we will focus on the scheduling problem, which
is well known in the literature and a focus in manufacturing control. In scheduling problems, human factors
(e.g. fatigue) are seldom investigated, since they bring a high complexity related to human variability
(individual characteristics, heterogeneity) as well as the human unpredictability (human errors). Furthermore,
the link between human factors and scheduling is a challenge, since scheduling depends on human factors,
depending themselves on a proposed schedule.

In order to consider these human factors, the proposed agent model, based on discrete event state model, will
integrate some states related to human factors, evolving in short (fatigue), mid (cognitive charge) and long
(mood) time horizon. These states will evolve according to the predefined schedule, i.e. according to the
sequence of actions computed during the decision-making process. The decision making process will use the
state, including the human factors, as in state feedback control. In order to observe the human factors' states,
predictive methods (which can be from artificial intelligence) will be used to estimate the factors, by using
other measured states such as the efficiency (or lack of efficiency) of the actions performed by the agent.

In order to show the applicability of proposed methods, the flexible manufacturing cell "TRACILOGIS" will be
used.
Keywords:
Internet of Social Agents, Intelligent manufacturing control, Human factors
Conditions:
The duration of the thesis will be 3 years funded by a doctoral contract from the University of Lorraine
the remuneration is that of a classical doctoral contract
Thesis carried out at CRAN

Expected profile:
- Master in computer engineering, industrial engineering, automatic
- Goof level of written and oral English
Department(s): 
Eco-Technic systems engineering
Funds:
Phd funding