Kannisto.org

Petri Kannisto's homepage – about software systems and research

System Architecture for Mastering Machine Parameter Optimisation

P. Kannisto, D. Hästbacka, and S. Kuikka, "System Architecture for Mastering Machine Parameter Optimisation", Computers in Industry, vol. 85, pp. 39-47, 2017. DOI: 10.1016/j.compind.2016.12.006

ISSN0166-3615
Cite The citations cannot be guaranteed to be in the correct format!
Bibtex
@article{kannisto_et_al2017system,
    year = {2017},
    author = {Kannisto, Petri and H{\"a}stbacka, David and Kuikka, Seppo},
    title = {System Architecture for Mastering Machine Parameter Optimisation},
    pages = {39-47},
    journal = {Computers in Industry},
    volume = {85},
    issn = {0166-3615},
    doi = {10.1016/j.compind.2016.12.006}
}
IEEEtran
P. Kannisto, D. Hästbacka, and S. Kuikka, "System Architecture for Mastering Machine Parameter Optimisation", Computers in Industry, vol. 85, pp. 39-47, 2017. DOI: 10.1016/j.compind.2016.12.006
APA
Kannisto, P., Hästbacka, D., & Kuikka, S. (2017). System Architecture for Mastering Machine Parameter Optimisation. Computers in Industry, 85, 39-47. https://doi.org/10.1016/j.compind.2016.12.006
Full text

Related items at Kannisto.org

Research project(s): D2I

Keywords

Distributed systems; Knowledge management; Performance optimisation; Mobile machines

Abstract

In mobile machines, as well as in manufacturing, the overall productivity is essential for business competitiveness. As the operation of a modern mobile machine is affected by various parameters, they need to be tuned to reach an optimal performance – however, due to machine complexity, parameter optimisation is difficult for a typical operator. To enable parameter optimisation locally in machines, this article presents a system architecture to generate information and knowledge from machine fleet data and to utilise them in machine operations in the field. Measurement data is collected and analysed to discover the associations between machine performance and parameter values. While some results are plain statistical distributions, any resulting more sophisticated domain knowledge is stored as rules. Rule-based reasoning enables a zone of interoperation between the information system and domain experts. Once information and knowledge have been generated, they are made available to machines that run the actual parameter assessment application. Results made with forestry data indicate that the system has a considerable potential to improve machine productivity.