Metaheuristic approaches for scheduling of multipurpose batch plants
No Thumbnail Available
Date
2018
Authors
Woolway, Mathew John
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The field of batch chemical process has seen a significant rise in research
over the last five decades as changes in the economic climate have lead to an
increased demand for the manufacturing of high-value small-volume products.
Due to the dependency on time, batch processes are considerably more complex
than their continuous process counterparts. The predominant approach in
batch process literature makes use of mathematical programming, whereby binary
variables are utilised to indicate the assignment of certain tasks to capable
units. This mathematical programming strategy, coupled with the aforementioned
time complexity can lead to computational intractability due to the extended
enumeration of binary variables. In this thesis, the reduction of computational time
requiredinthesolutionofmultipurposebatchplantschedulingisconsidered.
Due to the infeasible computational times required to solve mathematical
programming models in multipurpose batch plant scheduling, often close-to
optimal solutions rather than global optimal solutions are accepted. If close-to
optimal solutions are acceptable then it is reasonable to explore non-deterministic
metaheuristic strategies to reduce the required computational time. In order to apply these strategies, generalised frameworks consistent with metaheuristic
approaches are necessary. Presently, no decoupled generalised framework suitable
for various metaheuristic implementation exists in the literature.
As a result, this thesis presents two novel mathematical frameworks for the
representation of batch scheduling. Specifically, one framework for discrete-time
approaches and another framework for continuous-time approaches. In each
framework, two well-known literature examples are considered. In addition, three
metaheuristic techniques are applied to these literature examples, namely, genetic
algorithms (GA), simulated annealing (SA) and migrating bird optimisation (MBO).
The resultant framework allows for experimentation of 12 variants of the literature
examplestobeinvestigated,whichcanbecomparedtothecurrentlyacceptedmixed
integerlinearprogramming(MILP)approach.
In the aforementioned experiment, simulated results with the metaheuristics
implemented under the newly introduced frameworks showed a reduction in
computational time of up to 99.96% in the discrete-time approach and 99.68% in
the continuous-time approach. Additionally, the genetic algorithm showed to be
the best performer of the metaheuristic suite, often obtaining the global optimum
in short-time horizons and close-to-optimal solutions in the medium-to-long
time horizons. Furthermore, parallel implementations were explored and showed
additional time reduction would be possible, with certain workloads terminating 2
ordersofmagnitudelessincomputationaltimethanserialimplementations.
Theresultsshowtheapplicationofmetaheuristicstotheschedulingofmultipurpose
batch plants are indeed appropriate and are able to obtain close-to-optimal
solutions to that of their MILP counterparts at considerably reduced computational
times.
Description
A thesis submitted in fulfilment of the requirements for the Degree of Doctor of Philosophy in the School of Chemical and Metallurgical Engineering, University of the Witwatersrand, Johannesburg, 2018
Keywords
Citation
Woolway, Matthew John (2018) A metaheuristic approach to scheduling of multipurpose batch plants, University of the Witwatersrand, Johannesburg, https://hdl.handle.net/10539/27317