Swarm particle gradient descent algorithm based on improved genetic algorithm
A gradient descent algorithm and improved genetic algorithm technology, applied in genetic rules, calculations, calculation models, etc., can solve problems such as fast convergence speed, low success rate, and inability to have both at the same time, and achieve the effect of accelerating the evolution rate
Pending Publication Date: 2020-10-13
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, since the algorithm is a local search algorithm, it is not suitable for solving complex nonlinear optimization problems
Therefore, none of the above algorithms can have fast convergence speed and strong global search ability at the same time, and this feature is the future development direction of search algorithms, and the above inherent algorithms all have a higher probability of converging to a local optimal solution
In order to solve the problem of slow convergence speed and low success rate of convergence to the global optimal solution under the complex function solution conditions of the inherent algorithm, the present invention firstly improves the genetic algorithm to improve the global search ability and convergence speed of the algorithm
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The algorithm flow chart is attached figure 1 , the pseudo code of the algorithm is as follows:
[0037]
[0038]
[0039] Two optimization experiments were carried out to verify the superiority of the new algorithm compared with the traditional genetic algorithm and the improved genetic algorithm.
[0040] Experiment 1: The analytical formula of the test function is as follows,
[0041]
[0042] The purpose is to find the minimum value of the function in the range of x,y∈[0,10]. It is known that the minimum value of this function in the interval [0,10] is -0.1913, at this time x=7.7984, y=6.2019 or x=6.2019, y=7.7984. The schematic diagram of the function in the definition domain and the position of the minimum value are shown in the appendix figure 2 .
[0043] The population size of the genetic algorithm is set to 100, the result precision is 0.0001, the mating probability is 0.24, and the upper limit of the number of iterations is 200. This experiment ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
According to a swarm particle gradient descent algorithm based on an improved genetic algorithm, a globally optimal solution under a complex function condition can be quickly and accurately searched,and the swarm particle gradient descent algorithm comprises the following steps of: generating whether an initial swarm meets a termination condition or not, and calculating a fitness value of each individual; screening genetic operators, generating a new population with a gradient descent method acting on each individual, calculating the fitness value of each individual, and performing crossovermutation operation to generate the new population. The improvement method of the genetic algorithm comprises the steps that the first five individuals with the maximum fitness value in a population are reserved, and probability selection is conducted on the remaining new population individuals through a wheel disc selection method; a parallel computing thought and an evolutionary mechanism of thegenetic algorithm are introduced into a gradient descent method, namely, original single-point optimization is changed into group optimization, and a new group closer to an optimal solution continuously exists while the optimal solution is searched in the gradient direction.
Description
technical field [0001] The invention relates to an optimization method for decision-making and site selection, and relates to a function optimization algorithm, especially capable of solving optimization problems under complex function conditions. Background technique [0002] The range of multi-objective programming problems in the fields of artificial intelligence network training, automatic control, pattern recognition, etc. is extremely wide, among which the optimization method of decision-making and location selection is very meaningful in reality: such as the location selection problem of rescue bases. The location of the rescue base needs to consider the rescue distance, rescue time, construction cost, construction feasibility and other issues. This problem is a multi-objective programming problem, and an adaptive function consistent with its goal can be established. According to the underlying parameter variables in the adaptive function, For example, the location of...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06N3/00G06N3/12G06F17/15
CPCG06F17/15G06N3/006G06N3/126
Inventor单雨龙赵世军李秋涵
OwnerNAT UNIV OF DEFENSE TECH