Journal
JOURNAL OF INTELLIGENT MANUFACTURING
Volume 30, Issue 3, Pages 1483-1495Publisher
SPRINGER
DOI: 10.1007/s10845-018-1440-9
Keywords
Big data analytics; Machining optimisation; Hybrid algorithm; Deep belief network; Genetic algorithm
Funding
- National Natural Science Foundation of China [51605121]
Ask authors/readers for more resources
Currently, machine tool selection, cutting tool selection and machining conditions determination are not usually performed at the same time but progressively, which may lead to suboptimal or trade-off solutions. Targeting this issue, this paper proposes a big data analytics based optimisation method for enriched Distributed Process Planning by considering machine tool selection, cutting tool selection and machining conditions determination simultaneously. Within the context, the machining resources are represented by data attributes, i.e. workpiece, machining requirement, machine tool, cutting tool, machine conditions, machining process and machining result. Consequently, the problem of machining optimisation can be treated as a statistic problem and solved by a hybrid algorithm. Regarding the algorithm, artificial neural networks based models are trained by machining data and used as optimisation objectives, whereas analytical hierarchy process is adopted to decide the weights of the multi-objective optimisation; and evolutionary algorithm or swarm intelligence is proposed to perform the optimisation. Finally, the results of a simplified proof-of-concept case study are reported to validate the proposed approach, where a Deep Belief Network model was trained by a set of hypothetic data and used to calculate the fitness of a genetic algorithm.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available