Abstract
The purpose of this paper is to establish a decision-making system for assembly clearance parameters and machine quality level by analyzing the data of assembly clearance parameters of diesel engine. Accordingly, we present an extension of the rough set theory based on mixed-integer linear programming (MILP) for rough set-based classification (MILP-FRST). Traditional rough set theory has two shortcomings. First, it is sensitive to noise data, resulting in a low accuracy of decision systems based on rough sets. Second, in the classification problem based on rough sets, the attributes cannot be automatically determined. MILP-FRST has the advantages of MILP in resisting noisy data and has the ability to select attributes flexibly and automatically. In order to prove the validity and advantages of the proposed model, we used the machine quality data and assembly clearance data of 29 diesel engines of a certain type to validate the proposed model. Experiments show that the proposed decision-making method based on MILP-FRST model can accurately determine the quality level of the whole machine according to the assembly clearance parameters.
Highlights
Diesel engine is the power core of the ship
Previous studies on the relationship between assembly clearance and machine quality have mainly focused on the mechanical principle, while the data mining method is still less used to mine the relationship between assembly clearance and machine quality
Zhang et al proposed a multi-objective linear programming method based on the rough set, to develop a classification for data mining
Summary
Diesel engine is the power core of the ship. In the manufacturing process of the diesel engine, the assembly quality affects the performance indexes of the diesel engine, which is an important factor to measure the quality of the whole engine. Zhang et al proposed a multi-objective linear programming method based on the rough set, to develop a classification for data mining. Because nonlinear models are considered to be the only way to describe the rough set, there are no studies on the application of linear programming methods to optimize decision-making models based on the rough set. In this study, we extend the rough set theory via mixed-integer linear programming and we propose a model called the mixed-integer linear programming model for rough set-based classification with flexible attribute selection (in short, MILP-FRST). This model includes the advantages of MILP in resisting noisy data, and it has the ability to select attributes flexibly and automatically.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
