YXS
/
nmWTAI-Platform
8
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
290 Commits
25 Branches
0 Tags
128 MiB
C++ 53.7%
C 34.2%
Assembly 3.2%
HTML 2.2%
Python 2.1%
Other 4.4%
 
 
 
 
 
 
feature/AutoFit-Optimize-20260914
develop
feature/nmNum-postprocessing-view-20260910
feature/Adapt-Autofit-20260904
feature/nmNum-multi-gauge-record
feature/pebi-result-snapshot-20260831
feature/grid-solver-workflow-20260827
feature/AutoFit-Optimize-20260826
feature/refactor-numerical-model-panel-20260824
feature/AutoFit-Optimize-20260821
feature/refactor-well-editor-20260821
feature/AutoFit-Benchmark-20260820
feature/Auotfit-20260817
feature/PebiSolver-Integration-20260818
feature/ReservoirPropertiesDlg-Refactoring-20260813
feature/MultiWellAutoFit-20260805
feature/Interpolation-20260803
feature/prepost-render-refactor
feature/Model-20260625
feature/nm-para-property-20260615
feature/Merge-Framework-20260721
feature/ModelOpt20260526
feature/UI-20260528
feature/DialogBox-20260526
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'cd8bd9bafe'
${ noResults }
Go to file
lvjunjie cd8bd9bafe perf(nmNum): 优化 LM 灵敏度重建时机与采样加密衔接 
- 取消累计步长触发重建，连续两步实际改善不足预测的 25% 时刷新模型
- 将兜底刷新间隔调整为接受 10 步，避免微小预测量和单纯约束拒绝触发重建
- 合并临近的采样加密与灵敏度重建，提前考虑剩余求解预算
- 阶段切换时清除旧目标的预测失准计数，保留必要的失败恢复与停滞确认
- 补充重建原因日志、跟踪记录及中文翻译
 		2 weeks ago
3rd feat(nmNum): 集成PEBI CPU加速求解器配置 2 months ago
Bin perf(nmNum): 优化 LM 灵敏度重建时机与采样加密衔接 2 weeks ago
Include feat(nmNum): 新增 LM 高度与形状预调整的三阶段拟合 2 weeks ago
ML 统一代理模型与相态场景路径 2 months ago
Src/nmNum perf(nmNum): 优化 LM 灵敏度重建时机与采样加密衔接 2 weeks ago
Src4 refactor(nmNum): 重构编辑井并统一参数字段体系 1 month ago
.gitignore Merge branch 'feature/ModelOpt20260526' into develop 3 months ago
README.md feat: initial commit 4 months ago

README.md

nmWATI-2026