Method and system for evolutionary high-dimensional multi-objective optimization based on mixed preference model
A multi-objective optimization and model technology, applied in multi-objective optimization, genetic models, CAD based on constraints, etc., can solve problems such as algorithm performance differences
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach
[0077] Figure 4 is a specific flowchart of the evolutionary high-dimensional multi-objective optimization method based on the mixed preference model, such as Figure 4 As shown, the evolutionary high-dimensional multi-objective optimization method based on the mixed preference model includes the following steps:
[0078] Step 1: Randomly generate an initial population P of size N 0 ;
[0079] The subpopulation Q is generated by the recombination operator through crossover and mutation t , and jointly update the current population P with Pt t =P t ∪Q t , then its size is 2N;
[0080] Step 2: Build a mixed preference model according to the preference information preset preference area;
[0081] (1) Preference area description
[0082] For an M-dimensional multi-objective optimization problem, decision makers set their preference areas in different target dimensions according to their preferences, and the preference areas in the M-dimensional space are given by express...
Embodiment 1
[0146] An embodiment of the present invention provides an evolutionary high-dimensional multi-objective optimization device based on a mixed preference model, such as Figure 11 As shown, it includes: a memory 1100, a processor 1102, and a computer program stored on the memory 1100 and operable on the processor 1102. When the computer program is executed by the processor 1102, the following method steps are implemented:
[0147] S1. Construct a mixed preference model, the specific method is:
[0148] S101. According to the preference of the decision-maker, set its preference area in each dimensional space to form a target area;
[0149] Specifically, the preference area on the M-dimensional space is represented by expressed in the form of and Denote the lower and upper bounds of the preference region on the j-th dimensional space, respectively.
[0150] S102. Generate a group of uniformly distributed reference points on the unit hyperplane, and constrain the reference p...
Embodiment 2
[0171] An embodiment of the present invention provides a computer-readable storage medium, where a program for realizing information transmission is stored on the computer-readable storage medium, and when the program is executed by the processor 1102, the following method steps are implemented:
[0172] S1. Construct a mixed preference model, the specific method is:
[0173] S101. According to the preference of the decision-maker, set its preference area in each dimensional space to form a target area;
[0174] Specifically, the preference area on the M-dimensional space is represented by expressed in the form of and Denote the lower and upper bounds of the preference region on the j-th dimensional space, respectively.
[0175] S102. Generate a group of uniformly distributed reference points on the unit hyperplane, and constrain the reference points to the unit hypersphere pointing to the target area through coordinate transformation based on the target area;
[0176] ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More