thesis.pdf (8.1 MB)
Download file

Production scheduling as joint cognitive work

Download (8.1 MB)
posted on 12.04.2021, 07:48 by Peter Denno
The trend over the past four decades to move manufacturing operations to low-wage countries has left many developed nations with diminished manufacturing skills. Manufacturing’s current trajectory appears aimed at automating away human roles in tasks requiring cognitive skills much as it has automated away human roles in tasks requiring physical skills. This may prove difficult owing to the diversity of industrial contexts and skills involved in manufacturing. It may be possible, however, for humans to perform some cognitive tasks (such as production scheduling) jointly with artificial intelligence (AI) machine agents. This thesis reports the research undertaken to improve outcomes in the cognitive task of formulating production scheduling solutions. The aim is to develop an effective methodology by which the work of production scheduling can be divided among human and machine agents, then to develop tools to support the methodology. Requirements on joint cognitive work were established through a detailed literature review and an industrial pilot. These efforts revealed that, though machine guidance and validation of analysts’ scheduling solutions is theoretically possible, research gaps make this joint cognitive work impractical. Specifically, difficulties are encountered in: (1) analysts translating requirements into analytical models; (2) machine agents recognizing the scheduling formulation analysts are attempting; and (3) both analysts and machine agents staying apprised of emerging impediments to production. Analysis of the requirements and research gaps pointed to the development of a sociotechnical system in which the joint work is performed as the manipulation of two shared objects: a notebook for formulating the scheduling problem, and computer simulations highlighting current production challenges. Methodology and software were developed to support the shared objects and to validate their use in addressing the research gaps.



  • Mechanical, Electrical and Manufacturing Engineering


Loughborough University

Rights holder

© Peter Owen Denno

Publication date



A Doctoral Thesis. Submitted in partial fulfilment of the requirements for the award of the degree of Doctor of Philosophy of Loughborough University.




Charles E. Dickerson ; Jennifer A. Harding

Qualification name


Qualification level


This submission includes a signed certificate in addition to the thesis file(s)

I have submitted a signed certificate