Emanuele Carpanzano; Andrea Bettoni

doi:10.19080/PBSIJ.2021.16.555945

Mini Review

Human Factors in Advanced Industrial Systems: An Innovative Framework to Design Balanced Cognitive-Digital Closed Loop Control Solutions

Emanuele Carpanzano* , Andrea Bettoni

Department of Innovative Technologies, University of Applied Sciences and Arts of Southern Switzerland, Switzerland

Submission: December 29, 2020; Published: April 12, 2021

*Corresponding author: Emanuele Carpanzano, Galleria 2, CH-6928 Manno, Department of Innovative Technologies University of Applied Sciences and Arts of Southern Switzerland, Switzerland

How to cite this article:Emanuele C, Andrea B. Human Factors in Advanced Industrial Systems: An Innovative Framework to Design Balanced Cognitive-Digital Closed Loop Control Solutions. Psychol Behav Sci Int J .2021; 16(4): 555945. DOI: 10.19080/PBSIJ.2019.10.555945.

Abstract

The impact of digitalisation on advanced industrial systems is changing the relationship between humans, the technological system and the organization framework. Due to growing complexity of industrial processes and their digital control systems, it is of major relevance to consider industrial workers’ safety and psychophysiological health. An innovative framework to represent and design cognitive-digital closed loop control solutions is proposed, so as to achieve production performance as well as workers safety and well-being in a balanced way. Industrial application cases, experienced benefits and future perspectives are addressed throughout the paper.

Keywords: Digitalisation; Industrial processes; Control systems; Human factors

Introduction

Digitalization is strongly changing industrial systems and related value chains. In order to deal with continuous product innovation dynamics, production processes have to increase flexibility and embedded intelligence at different levels, and to integrate advanced control and automation systems [1]. As a consequence, it is becoming of major relevance to balance such technological innovations with organizational aspects and human factors, in order to reduce human errors, increase productivity, and enhance safety and comfort of industry workers [2,3]. Specifically, psychological and physiological principles have to be considered in the design of industrial plants, with a specific focus on the interaction between the human and the digital control and automation system [4,5].

This paper outlines a framework to design industrial automation systems balancing production performance with human aspects, by means of a reference model integrating humans in the closed loop factory automation system. The framework is described, outlining its main features, and application cases in real world industrial settings are addressed to highlight the experienced benefits and the potential of future research.

A Novel Framework to Design Cognitive-Digital Closed Loop Industrial Control Systems

In order to represent operators’ safety and well-being, a systemic model has to be introduced that includes the cognitive and physical aspects of operators interacting with the industrial control and automation system [5]. Relevant facets to be considered are: the human operator; the team; the organization; the physical environment; the social environment; the tools (including technology, control and automation systems); the rules and procedures; as well as the execution tasks [6]. These features can be regarded as interacting, like fragments of a bowl that dynamically move in order to fill in the gaps that may arise at their borders (Figure 1).

The water in the bowl represents the operators’ well-being, whose optimal level depends on the dynamic interaction among the main aspects of a system; well-being level is determined by the gaps that the fragments create at their borders. Sometimes an action aimed at increasing well-being could consider only one fragment; but changing just one part could lead to breaking the bowl if the other elements do not adapt to it. The design of digital industrial automation systems should be guided by considering this model so as to promote harmonization of the fragments’ behaviour. In particular, adaptive automation could provide a flexible fragment that copes with the inherent variability of the production system coming from human and organizational factors, process changes and productivity needs [1,7]. The constant adaptation has to enable the system to fill the gaps ensuring operators’ overall safety and well-being.

The above-mentioned vision can be translated into a conceptual and modelling framework that supports a seamless adoption of a human-in-the-loop adaptive automation approach reducing the risk of negative gaps. As a matter of fact, by optimizing the capabilities residing in the human dimension of the factory and the digital automation’s full potential within a unique coherent framework, it becomes possible to fully enhance industrial productivity and human workers safety and well-being at the same time [4,5].

Figure 2 shows the proposed human-in-the-loop factory control and automation system reference model. Such a framework includes the human as a fully integrated part of the whole process, considering his two dimensions as active operator and decision maker. As a matter of fact, the human acts at operational level directly taking part to the production process, as well as at decision making level, in synergy with supervision and execution planning tools of the industrial automation systems. Within the proposed digital-cognitive automation framework, goals specifically aimed at enhancing working conditions operate in parallel with traditional performance targets. Consequently, a stream of physiological measures is constantly monitored to detect in real time any deviations from personalized safe patterns, and propose actions aimed at mitigating the cognitive and physical demand that the worker is experiencing [8]. Moreover, reconfigurable automation policies that apply in the distributed automation structure [7] explore and possibly eliminate the sources of cognitive and physical gaps such as skill mismatching and alienating duties.

Scientific and Technological Challenges to be Faced

In order to fully exploit the proposed framework, different scientific and technological challenges have to be faced, also considering the specific application domain and the overall objectives and requirements to be achieved as far as production performance and human safety and well-being are concerned. First, the production and human key performance indicators (KPIs) have to be defined in a clear and measurable way. Therefore, variable production needs in both quantitative and qualitative terms have to be properly identified, considering also the variations of products during the production system life cycle. Moreover, the requirements related to human workers safety and well-being have to be specified too, identifying the related psychological and physiological variables and parameters to be monitored and evaluated [5,8].

Secondly, suitable and reliable sensing and monitoring devices have to be adopted in order to properly measure the production system performance and the human workers parameters and dynamic variables of interest. To achieve such an objective, innovative wearable technology, sensor networks and data fusion methods and tools need to be exploited and integrated [9]. A third relevant module of the proposed framework are methodologies and instruments to identify the needed control actions based on the measured signals, variables and parameters, and on the values of actual KPIs compared to the desired objectives and requirements. Such methodologies may be based on different mathematical and heuristic approaches, including also advanced methods based on artificial intelligence techniques like machine learning [5,8]. Finally, advanced control system methods, like model predictive control solutions, have to be integrated to implement the industrial automation systems at different levels, and innovative decision support tools have to be adopted to support the human decision makers for complex planning and execution tasks [1,7].

Application Cases and Experienced Benefits

The exploitation of the proposed framework has to be adapted to each specific application case, considering the involved industrial sector, the specific production process features, up to each single operating machine, and the involved human aspects, up to the personal profile of each worker, so as to guarantee his/her personal safety and well-being. Real world industrial application cases are discussed in [5,9,10].

In [5] an application case in the white-goods industry is illustrated, where the presented framework is adopted with specific reference to the design of adaptive workplaces, according to the characteristics and conditions of the individual workers. In such a work, human-centered workplaces are developed by means of several tools used in three distinct main phases: knowledge creation, production line design and line operation [8]. For the validation of the approach and developed tools, two lines, one for microwave ovens and another for fridge production, are considered. The improved workplace adaptability results in the reduction of cumulative trauma disorders and psychological stress. The availability of an all-encompassing digital solution capable to characterize, from a human-centric perspective, both workers and production lines allows to integrate all necessary human-related information and to support production facilities improvement in terms of skill-matching, ergonomics and safety. Furthermore, the integration of multi-perspective tools provides environments that promote awareness of all the human-related aspects at a glance, thus fostering first-time-right solutions for effective industrial production capacity and reducing the several design iterations that were necessary before adopting the presented approach.

In [9] the proposed general framework is applied in an injection molding manufacturing line in which operators execute complex sequences of different tasks, while changing tools and body position. As shown in Figure 3, workers are equipped with wearable devices recording physiological data, allowing to compare mental and physical stress levels detected in the different working setups and configurations. In particular, by introducing a physiological monitoring system and a smart decision-maker based on machine learning techniques, relief from fatigue and mental stress is pursued by dynamically adjusting the level of support offered to the human operator through a collaborative robot. The experimentally obtained results, collected through quantitative and subjective indicators, show a reduction of the physical and mental workload of the operators as well as an overall productivity increase.

Finally, [10] shows the application of the proposed framework within a furniture production system where product diversification combines with large scale production, thus requiring a fast paced and strongly automated working environment. In this context, and specifically in the pre-assembly operations, a novel solution is implemented based on augmented reality technology and aimed at supporting the operator in keeping an updated mental model of the working conditions. In particular, an augmented reality headset provides just-in-time knowledge whose level of detail and content are adjusted to the worker’s static characteristics, such as competence and past experience, but also to his/her current cognitive workload, thanks to a device capable to infer stress levels by measuring variances in the breathing patterns. The system relies heavily on the modelling of the interactions between the worker and the surrounding environment. The experienced results show that by leveraging a product model that describes the product’s components and their assembly instructions, a task model capable to measure task progression at any time and the mentioned worker and stress models, it becomes possible to properly balance the working operations and take proper countermeasures whenever critical cognitive workload conditions occur.

Concluding Remarks and Future Research Perspectives

Future smart factories, integrating advanced digital solutions, need new approaches and instruments to balance the cognitive and physical workload of operators with respect to the industrial control and automation systems operations, in order to guarantee human workers overall safety and well-being.

In the present paper an innovative general framework is introduced to design human-aware adaptive automation systems. According to this framework, well-being is achievable by implementing adaptability and flexibility within a sociotechnical system based on a cognitive-digital closed loop control approach. As a matter of fact, the industrial automation systems become the keystone of the proposed human-in-the-loop adaptive approach to production. The new factory automation solution integrates seamlessly human and digital decision-making by monitoring production performances and workers’ physiological and psychophysical parameters, and by closing the control and execution loops, so as to optimize both production and workers well-being related KPIs. The main components of the proposed framework have been described in the paper outlining the major scientific and technological challenges to be addressed in their future development and adoption in industrial practice. Furthermore, real world application cases have been described to highlight experienced advantages and benefits of the illustrated approach. The results obtained so far prove, qualitatively and quantitatively, that the integration of the human factors analysis, within automation design, is a crucial element for a synergic improvement of manufacturing performance and human safety and well-being at once.

Future work needs to address and further develop methods and tools to cope with the addressed scientific and technological challenges to exploit the proposed framework in different application domains. Nowadays, due to the fast digitalization of industrial processes, the human-automation synergy is fundamental for a sound and human aware development and adoption of new emerging production paradigms. As a matter of fact, the acceleration of scientific and technological innovations will make the industrial digitalization and automation roles more and more important and pervasive. Consequently, the future evolution of manufacturing industry should tackle the challenge to properly balance the industrial targets with the workers well being, by means of human-in-the-loop adaptive automation systems, integrating advanced sensing and monitoring devices, as well as novel control and decision making techniques.