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.
 
 
 
 
 
 
Go to file
lvjunjie 529655f205 refactor(nmNum): 将拟合流程改为高度预调和双目标联合 LM
- 保留渗透率高度预调,移除逐参数形状扫描及井储、表皮复查
- 联合 LM 先优化整体形状误差,再优化总误差,共用步长、阻尼和停滞规则
- 形状达标、确认停滞或达到额度后切换目标,两段独立计算迭代和求解额度
- 更新拟合日志和策略元数据,通过编译语法检查及联合 LM 行为验证
4 days ago
3rd feat(nmNum): 集成PEBI CPU加速求解器配置 2 months ago
Bin fix(nmNum): 补充网格尺寸保存校验和中文错误提示 4 days ago
Include refactor(nmNum): 移除分层采样并按对数时间跨度确定采样点数 4 days ago
ML 统一代理模型与相态场景路径 2 months ago
Src/nmNum refactor(nmNum): 将拟合流程改为高度预调和双目标联合 LM 4 days 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