Method for achieving shielding mortar performance optimization based on BP neural network algorithm and genetic algorithm
A BP neural network and genetic algorithm technology, applied in the field of shield mortar mixing optimization, can solve problems such as poor mix ratio and poor performance
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2016-12-07
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of shield-tunnel mortar mixing optimization methods, in particular to a shield-tunnel mortar performance optimization method based on BP neural network and genetic algorithm. Background technique
[0002] Shield mortar is the grout for grouting behind the shield wall. The materials it mixes include cement, fly ash, bentonite, lime, sand, and water. Its main properties include bleeding rate, consistency, strength, and density. During the mixing process, different mix ratios have different effects on the performance of mortar.
[0003] In engineering, the performance of the mixed mortar slurry is poor due to poor mix ratio. Therefore, whether there is an optimal state in the mixing ratio is a simple and effective way to achieve performance optimization. The mixing process is a complex nonlinear system that cannot be described by simple mathematical formulas, and the mortar mixing ratio experiment has laid the foundatio...
Examples
Embodiment Construction
[0041] The method for optimizing the performance of shield tunneling mortar based on BP neural network and genetic algorithm in this embodiment includes the following steps: selecting a plurality of influencing parameters that affect the performance of the mortar during the mortar mixing process and performance observation parameters that can reflect the performance of the mortar; Prepare multiple groups of mortar samples under the influence parameters, and obtain the influence parameter sample matrix , collect the performance observation parameters of each group of mortar samples, and obtain the sample matrix with the influencing parameters The corresponding observation parameter sample matrix ; Respectively for the influence parameter sample matrix and observation parameter sample matrix Perform normalization processing to obtain sample matrix X and performance sample matrix Y respectively; use the sample matrix X as input and the performance sample matrix Y as output...