diff --git a/Include/nmNum/nmCalculation/nmCalculationAutoFitLM.h b/Include/nmNum/nmCalculation/nmCalculationAutoFitLM.h index 06350bc9..3255a4f3 100644 --- a/Include/nmNum/nmCalculation/nmCalculationAutoFitLM.h +++ b/Include/nmNum/nmCalculation/nmCalculationAutoFitLM.h @@ -12,29 +12,14 @@ #include "nmCalculation_global.h" -// 固定对数时间窗口的误差诊断。时间边界为不含重叠区的基础边界； -// rmsError 是局部加权均方根，energy 是对整体残差能量的贡献。 -struct AutoFitTimeWindowLM { - double timeMin; - double timeMax; - double weightSum; - double rmsError; - double energy; - - AutoFitTimeWindowLM() - : timeMin(0.0), timeMax(0.0), weightSum(0.0), rmsError(0.0), energy(0.0) - {} -}; - // 双对数曲线误差分解。预调整使用纵向偏差，形状阶段使用双曲线斜率残差， -// 整体阶段只使用 total 接受候选；时间窗口和残差用于 Fisher 选参。 +// 整体阶段只使用 total 接受候选；两个 LM 目标均联合调整有效参数。 struct AutoFitObjectiveBreakdownLM { bool valid; double total; double pressureLoss; double derivativeLoss; QVector residualVector; - QVector timeWindows; double verticalCommonBias; double verticalLoss; bool verticalReliable; @@ -44,14 +29,6 @@ struct AutoFitObjectiveBreakdownLM { bool registrationAmbiguous; // 与整体误差共用 log-time 采样网格，斜率跨度约为完整对数时域的 10%。 QVector shapeResiduals; - // 前期数值和形状残差沿用同一网格与斜率跨度，均含第一窗口权重。 - // earlyParallelResiduals/Loss 沿用历史字段名，现为压力、导数分别匹配目标的形状误差。 - // earlyParallelBias 仍记录相对斜率偏差，仅供诊断。 - QVector earlyValueResiduals; - QVector earlyParallelResiduals; - double earlyValueLoss; - double earlyParallelLoss; - double earlyParallelBias; double pressureVerticalBias; double derivativeVerticalBias; double shapeLoss; @@ -71,9 +48,6 @@ struct AutoFitObjectiveBreakdownLM { , horizontalLoss(std::numeric_limits::quiet_NaN()) , horizontalReliable(false) , registrationAmbiguous(false) - , earlyValueLoss(std::numeric_limits::quiet_NaN()) - , earlyParallelLoss(std::numeric_limits::quiet_NaN()) - , earlyParallelBias(std::numeric_limits::quiet_NaN()) , pressureVerticalBias(0.0) , derivativeVerticalBias(0.0) , shapeLoss(std::numeric_limits::quiet_NaN()) diff --git a/Src/nmNum/nmCalculation/nmCalculationAutoFitLM.cpp b/Src/nmNum/nmCalculation/nmCalculationAutoFitLM.cpp index e50bc3b2..384c1dca 100644 --- a/Src/nmNum/nmCalculation/nmCalculationAutoFitLM.cpp +++ b/Src/nmNum/nmCalculation/nmCalculationAutoFitLM.cpp @@ -27,8 +27,6 @@ #endif static const bool kAutoFitDiagnosticTraceEnabled = true; -static const int kAutoFitTimeWindowCount = 4; -static const double kAutoFitTimeWindowOverlapRatio = 0.20; static const int kAutoFitIntervalsPerDecade = 20; static int autoFitShapeLag(int pointCount) @@ -37,57 +35,6 @@ static int autoFitShapeLag(int pointCount) return qMax(1, qRound((pointCount - 1) * 0.10)); } -static double autoFitTimeWindowWeight(double coordinate, int windowIndex) -{ - // 重叠区以基础边界为中心，总宽度为窗口宽度的 20%；相邻权重互补。 - const double width = 1.0 / kAutoFitTimeWindowCount; - const double overlap = width * kAutoFitTimeWindowOverlapRatio; - const double halfOverlap = overlap * 0.5; - const double pi = 3.14159265358979323846; - double weight = 1.0; - if(windowIndex > 0) { - double u = qBound(0.0, - (coordinate - windowIndex * width + halfOverlap) / overlap, - 1.0); - weight *= 0.5 * (1.0 - qCos(pi * u)); - } - if(windowIndex + 1 < kAutoFitTimeWindowCount) { - double u = qBound(0.0, - (coordinate - (windowIndex + 1) * width + halfOverlap) / overlap, - 1.0); - weight *= 0.5 * (1.0 + qCos(pi * u)); - } - return weight; -} - -static QVector calculateAutoFitTimeWindows( - const QVector& residualVector, double timeMin, double timeMax) -{ - // 残差前后两半分别为压力和导数，已包含各占一半及时间采样权重的归一化。 - const int pointCount = residualVector.size() / 2; - const double logMin = qLn(timeMin); - const double logSpan = qLn(timeMax) - logMin; - QVector windows(kAutoFitTimeWindowCount); - for(int k = 0; k < windows.size(); ++k) { - AutoFitTimeWindowLM& window = windows[k]; - window.timeMin = k == 0 ? timeMin - : qExp(logMin + logSpan * k / kAutoFitTimeWindowCount); - window.timeMax = k + 1 == windows.size() ? timeMax - : qExp(logMin + logSpan * (k + 1) / kAutoFitTimeWindowCount); - for(int i = 0; i < pointCount; ++i) { - const double weight = autoFitTimeWindowWeight( - static_cast(i) / (pointCount - 1), k); - window.weightSum += weight; - window.energy += weight * - (residualVector[i] * residualVector[i] + - residualVector[pointCount + i] * residualVector[pointCount + i]); - } - window.rmsError = window.weightSum > 0.0 - ? qSqrt(window.energy * pointCount / window.weightSum) : 0.0; - } - return windows; -} - static inline bool isFiniteNumber(double value) { #ifdef Q_OS_WIN @@ -279,26 +226,14 @@ static bool trustRegionResidualsValid( for(int i = 0; i < breakdown.shapeResiduals.size(); ++i) { if(!isFiniteNumber(breakdown.shapeResiduals[i])) return false; } - if(breakdown.earlyValueResiduals.size() != 2 * pointCount || - breakdown.earlyParallelResiduals.size() != 2 * slopeCount || - !isFiniteNumber(breakdown.earlyValueLoss) || !isFiniteNumber(breakdown.earlyParallelLoss) || - !isFiniteNumber(breakdown.earlyParallelBias)) return false; - for(int i = 0; i < breakdown.earlyValueResiduals.size(); ++i) { - if(!isFiniteNumber(breakdown.earlyValueResiduals[i])) return false; - } - for(int i = 0; i < breakdown.earlyParallelResiduals.size(); ++i) { - if(!isFiniteNumber(breakdown.earlyParallelResiduals[i])) return false; - } return true; } -// 数值、整体形状和前期形状残差共用一次求解，联合缓存供各子阶段复用。 +// 数值和整体形状残差共用一次求解，联合缓存供两个 LM 目标复用。 static QVector trustRegionFullResidual(const AutoFitObjectiveBreakdownLM& objective) { QVector residual = objective.residualVector; residual += objective.shapeResiduals; - residual += objective.earlyValueResiduals; - residual += objective.earlyParallelResiduals; return residual; } @@ -312,108 +247,6 @@ static double trustRegionSquaredNorm(const QVector& values) return sum; } -// 数值残差已含 sqrt(0.5 * 窗口权重)，相减并换底后得到 log10 间距的加权 RMS。 -// 不减去平均间距，保留“两条曲线整体离得太远”的信息；共同纵移会自然抵消。 -static double trustRegionEarlyGapLoss(const AutoFitObjectiveBreakdownLM& objective) -{ - const int count = objective.earlyValueResiduals.size() / 2; - double energy = 0.0; - for(int i = 0; i < count; ++i) { - const double difference = objective.earlyValueResiduals[i] - objective.earlyValueResiduals[count + i]; - energy += 2.0 * difference * difference; - } - return qSqrt(energy) / qLn(10.0); -} - -// 前期带符号的平均间距差：正值表示模拟比目标分得更开，负值表示更靠近。 -// 复用现有加权数值残差，恢复第一窗口的归一化权重，不用 RMS 推断偏差符号。 -static double trustRegionEarlyGapBias(const AutoFitObjectiveBreakdownLM& objective) -{ - const int count = objective.earlyValueResiduals.size() / 2; - QVector weights(count, 0.0); - double weightSum = 0.0; - for(int i = 0; i < count; ++i) { - weights[i] = autoFitTimeWindowWeight(static_cast(i) / (count - 1), 0) * - ((i == 0 || i == count - 1) ? 0.5 : 1.0); - weightSum += weights[i]; - } - double bias = 0.0; - for(int i = 0; i < count; ++i) { - bias += qSqrt(2.0 * weights[i] / weightSum) * - (objective.earlyValueResiduals[i] - objective.earlyValueResiduals[count + i]); - } - return bias / qLn(10.0); -} - -// 第一窗口的形状能量与局部 Fisher 使用相同的中心时间和重叠权重， -// 压力、导数同时参与；不重新插值或调用求解器。 -static double trustRegionEarlyShapeEnergy(const AutoFitObjectiveBreakdownLM& objective) -{ - const QVector& residual = objective.shapeResiduals; - const int pointCount = objective.residualVector.size() / 2; - const int lag = autoFitShapeLag(pointCount); - const int slopeCount = pointCount - lag; - double energy = 0.0; - for(int row = 0; row < residual.size(); ++row) { - const double coordinate = (row % slopeCount + lag * 0.5) / (pointCount - 1); - energy += autoFitTimeWindowWeight(coordinate, 0) * residual[row] * residual[row]; - } - return energy; -} - -// 前期复用整体形状的双曲线斜率残差，只按第一窗口重新加权并归一化。 -// 单独平移任一曲线不改变此指标；前期数值误差仅作诊断，不参与井储、表皮验收。 -static void populateEarlyWellboreMetrics(AutoFitObjectiveBreakdownLM* objective, - const QVector targetLogs[2], const QVector resultLogs[2], double logTimeSpan) -{ - const int count = targetLogs[0].size(); - QVector weights(count, 0.0); - double weightSum = 0.0; - for(int i = 0; i < count; ++i) { - weights[i] = autoFitTimeWindowWeight(static_cast(i) / (count - 1), 0) * - ((i == 0 || i == count - 1) ? 0.5 : 1.0); - weightSum += weights[i]; - } - objective->earlyValueResiduals.fill(0.0, 2 * count); - for(int i = 0; i < count; ++i) { - const double weight = weights[i] / weightSum; - for(int component = 0; component < 2; ++component) { - const int row = component * count + i; - const double scale = qSqrt(0.5 * weight); - objective->earlyValueResiduals[row] = scale * (resultLogs[component][i] - targetLogs[component][i]); - } - } - objective->earlyValueLoss = qSqrt(trustRegionSquaredNorm(objective->earlyValueResiduals)); - - // 复用整体形状的斜率跨度，窗口权重取区间中心，随采样数量同步变化。 - const int lag = autoFitShapeLag(count); - const int slopeCount = count - lag; - const double logTimeStep = logTimeSpan * lag / (count - 1); - QVector parallelWeights(slopeCount, 0.0); - double parallelWeightSum = 0.0; - for(int i = 0; i < slopeCount; ++i) { - parallelWeights[i] = autoFitTimeWindowWeight((i + lag * 0.5) / (count - 1), 0); - parallelWeightSum += parallelWeights[i]; - } - objective->earlyParallelResiduals.fill(0.0, 2 * slopeCount); - objective->earlyParallelBias = 0.0; - for(int i = 0; i < slopeCount; ++i) { - const double resultSlopeDifference = ((resultLogs[0][i + lag] - resultLogs[0][i]) - - (resultLogs[1][i + lag] - resultLogs[1][i])) / logTimeStep; - const double targetSlopeDifference = ((targetLogs[0][i + lag] - targetLogs[0][i]) - - (targetLogs[1][i + lag] - targetLogs[1][i])) / logTimeStep; - const double relativeSlopeError = resultSlopeDifference - targetSlopeDifference; - const double weight = parallelWeights[i] / parallelWeightSum; - objective->earlyParallelBias += weight * relativeSlopeError; - // 整体残差已含 sqrt(0.5 / slopeCount)，换成第一窗口权重后仍保持双曲线等权。 - // 压力、导数分别匹配目标；相对斜率偏差只保留为诊断，不参与前期验收。 - const double scale = qSqrt(slopeCount * weight); - objective->earlyParallelResiduals[i] = scale * objective->shapeResiduals[i]; - objective->earlyParallelResiduals[slopeCount + i] = scale * objective->shapeResiduals[slopeCount + i]; - } - objective->earlyParallelLoss = qSqrt(trustRegionSquaredNorm(objective->earlyParallelResiduals)); -} - // 计算同维向量内积；维度不一致表示局部模型无效，返回零让调用方放弃修正。 static double trustRegionDotProduct(const QVector& left, const QVector& right) @@ -498,65 +331,45 @@ static bool solveTrustRegionLinearSystem( return true; } -// Fisher 仅作为当前归一化坐标下的局部信息矩阵，不用于统计置信区间。 -struct TrustRegionFisher +// LM 正规方程所需的 J^T*J 与 J^T*r，使用当前归一化参数坐标。 +struct TrustRegionNormalEquations { QVector > matrix; QVector gradient; - explicit TrustRegionFisher(int dimensions = 0) + explicit TrustRegionNormalEquations(int dimensions = 0) : matrix(dimensions, QVector(dimensions, 0.0)) , gradient(dimensions, 0.0) {} }; -static QVector buildTrustRegionFisher( +static TrustRegionNormalEquations buildTrustRegionNormalEquations( const QVector >& jacobian, const QVector& residual, - const QVector& columnValid, - const QVector& coordinates = QVector()) + const QVector& columnValid) { - // 残差和 J 已包含压力/导数及时间采样权重，只再乘一次窗口权重。 - // 前半段是压力，后半段是导数；同一时间点的两行使用相同权重。 + // 残差和 J 已包含压力、导数及采样权重，直接累加整体矩阵，避免重复计权。 const int dimensions = columnValid.size(); - const int pointCount = residual.size() / 2; - QVector information( - kAutoFitTimeWindowCount + 1, TrustRegionFisher(dimensions)); - for(int k = 0; k < kAutoFitTimeWindowCount; ++k) { - TrustRegionFisher& local = information[k]; - for(int row = 0; row < residual.size(); ++row) { - const double weight = autoFitTimeWindowWeight( - coordinates.isEmpty() ? static_cast(row % pointCount) / (pointCount - 1) - : coordinates[row % pointCount], k); - for(int p = 0; p < dimensions; ++p) { - if(!columnValid[p]) { - continue; - } - local.gradient[p] += weight * jacobian[row][p] * residual[row]; - for(int q = 0; q <= p; ++q) { - if(columnValid[q]) { - local.matrix[p][q] += - weight * jacobian[row][p] * jacobian[row][q]; - } - } - } - } - // 互补窗口之和恢复全局 J^T*J 和 J^T*r，不能对各窗口再单独平均。 - TrustRegionFisher& global = information[kAutoFitTimeWindowCount]; + TrustRegionNormalEquations equations(dimensions); + for(int row = 0; row < residual.size(); ++row) { for(int p = 0; p < dimensions; ++p) { - global.gradient[p] += local.gradient[p]; + if(!columnValid[p]) continue; + equations.gradient[p] += jacobian[row][p] * residual[row]; for(int q = 0; q <= p; ++q) { - local.matrix[q][p] = local.matrix[p][q]; - global.matrix[p][q] += local.matrix[p][q]; - global.matrix[q][p] = global.matrix[p][q]; + if(columnValid[q]) + equations.matrix[p][q] += jacobian[row][p] * jacobian[row][q]; } } } - return information; + for(int p = 0; p < dimensions; ++p) { + for(int q = 0; q < p; ++q) + equations.matrix[q][p] = equations.matrix[p][q]; + } + return equations; } -static bool buildTrustRegionFisherStep( - const TrustRegionFisher& global, +static bool buildTrustRegionStep( + const TrustRegionNormalEquations& global, const QVector& selected, const QVector& coordinates, double damping, double trustRadius, double minimumStep, @@ -997,15 +810,8 @@ void nmCalculationAutoFitLM::writeTraceHeader() << "late_trend_reliable" << "registration_ambiguous"; - for(int k = 0; k < kAutoFitTimeWindowCount; ++k) { - const QString prefix = QString("window_%1_").arg(k + 1); - cols << prefix + "time_min" << prefix + "time_max" - << prefix + "weight_sum" << prefix + "rms_error" << prefix + "energy"; - } - cols << "sampling_mode" << "sampling_points" - << "pressure_vertical_bias" << "derivative_vertical_bias" << "first_window_shape_loss" - << "early_value_loss" << "early_parallel_loss" << "early_parallel_bias" << "early_gap_loss" << "early_gap_bias"; + << "pressure_vertical_bias" << "derivative_vertical_bias"; QTextStream out(&m_traceFile); out << cols.join(",") << "\n"; } @@ -1042,8 +848,8 @@ void nmCalculationAutoFitLM::writeTraceMetaFile() QTextStream out(&metaFile); out << "{\n"; - out << " \"schema_version\": 54,\n"; - out << " \"strategy\": \"permeability_height_then_joint_lm_shape_then_total\",\n"; + out << " \"schema_version\": 55,\n"; + out << " \"strategy\": \"permeability_height_then_joint_lm_total_for_vertical_well_else_shape_then_total\",\n"; out << " \"height_acceptance\": \"reliable_vertical_loss_decrease; no_shape_or_total_loss_constraint\",\n"; out << " \"shape_metric\": \"pressure_and_derivative_log_slopes_shared_sampling_grid_lag_round_10_percent_min_1\",\n"; out << " \"shape_parameter_selection\": \"all_valid_free_columns_joint_LM; no_single_parameter_sweep_or_wellbore_recheck\",\n"; @@ -1076,10 +882,8 @@ void nmCalculationAutoFitLM::writeTraceMetaFile() out << " \"max_iterations\": " << m_maxIterations << ",\n"; out << " \"target_error\": " << jsonNumber(m_targetError) << "\n"; out << " },\n"; - // 区间尚未冻结时写 null；首次有效评价后重写元数据，保存实际窗口基准。 - out << " \"time_windows\": {\n"; - out << " \"count\": " << kAutoFitTimeWindowCount << ",\n"; - out << " \"overlap_ratio\": " << jsonNumber(kAutoFitTimeWindowOverlapRatio) << ",\n"; + // 区间尚未冻结时写 null；首次有效评价后记录固定的误差比较范围。 + out << " \"comparison_time_range\": {\n"; out << " \"comparison_time_min\": " << (m_comparisonTimeMin > 0.0 ? jsonNumber(m_comparisonTimeMin) : QString("null")) << ",\n"; out << " \"comparison_time_max\": " @@ -1155,32 +959,10 @@ void nmCalculationAutoFitLM::writeTraceRow( } } - // 无效候选也补齐窗口列，保证轨迹每行结构一致。 - for(int k = 0; k < kAutoFitTimeWindowCount; ++k) { - if(objectiveBreakdown && objectiveBreakdown->valid && - k < objectiveBreakdown->timeWindows.size()) { - const AutoFitTimeWindowLM& window = objectiveBreakdown->timeWindows[k]; - cols << traceNumber(window.timeMin) << traceNumber(window.timeMax) - << traceNumber(window.weightSum) << traceNumber(window.rmsError) - << traceNumber(window.energy); - } else { - for(int i = 0; i < 5; ++i) { - cols << QString(); - } - } - } - cols << "log_uniform_per_decade" << (objectiveBreakdown ? QString::number(objectiveBreakdown->residualVector.size() / 2) : QString()) << (objectiveBreakdown ? traceNumber(objectiveBreakdown->pressureVerticalBias) : QString()) - << (objectiveBreakdown ? traceNumber(objectiveBreakdown->derivativeVerticalBias) : QString()) - << (objectiveBreakdown && objectiveBreakdown->valid - ? traceNumber(qSqrt(trustRegionEarlyShapeEnergy(*objectiveBreakdown))) : QString()) - << (objectiveBreakdown && objectiveBreakdown->valid ? traceNumber(objectiveBreakdown->earlyValueLoss) : QString()) - << (objectiveBreakdown && objectiveBreakdown->valid ? traceNumber(objectiveBreakdown->earlyParallelLoss) : QString()) - << (objectiveBreakdown && objectiveBreakdown->valid ? traceNumber(objectiveBreakdown->earlyParallelBias) : QString()) - << (objectiveBreakdown && objectiveBreakdown->valid ? traceNumber(trustRegionEarlyGapLoss(*objectiveBreakdown)) : QString()) - << (objectiveBreakdown && objectiveBreakdown->valid ? traceNumber(trustRegionEarlyGapBias(*objectiveBreakdown)) : QString()); + << (objectiveBreakdown ? traceNumber(objectiveBreakdown->derivativeVerticalBias) : QString()); QTextStream out(&m_traceFile); out << cols.join(",") << "\n"; m_traceFile.flush(); @@ -1824,6 +1606,10 @@ bool nmCalculationAutoFitLM::evaluateTrustRegionPoint( StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() { + // 本次拟合开始时按目标井的实际井型确定流程，普通直井跳过形状调整。 + nmDataAnalyzeManager* dataManager = nmDataAnalyzeManager::getCurrentInstance(); + nmDataWellBase* targetWell = dataManager ? dataManager->findWellByName(m_targetWellName) : nullptr; + const bool skipShapeStage = targetWell && targetWell->getWellType() == NM_WELL_MODEL::Vertical_Well; const int dimensions = getEnabledParameterCount(); if(dimensions <= 0 || m_enabledParamIndices.size() != dimensions) { m_lastError = tr("No valid parameters are available for trust-region fitting"); @@ -1863,11 +1649,10 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() const char* rebuildReason = QT_TR_NOOP("initial sensitivity model"); bool modelRebuiltAtMinimumRadius = false; bool stagnationConfirmationRequested = false; - bool globalFallbackAttempted = false; StopReasonLM stopReason = LM_MAX_ITERATIONS; // jacobian 的行对应固定采样的残差，列对应用户勾选的参数。 - // Fisher 按当前目标取数值或形状残差行，两段均使用所有勾选参数。 + // LM 按当前目标取数值或形状残差行，两段均使用所有勾选参数。 QVector > jacobian; QVector jacobianColumnValid(dimensions, false); @@ -2058,8 +1843,8 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() if(m_shouldStop) return LM_USER_STOPPED; if(completedIterations >= m_maxIterations) return LM_MAX_ITERATIONS; - // 原逐参数第二阶段已移除；同一个联合 LM 先匹配整体形状，再匹配总误差。 - bool shapeStage = true; + // 直井直接匹配总误差，其他井型仍先匹配整体形状，再匹配总误差。 + bool shapeStage = !skipShapeStage; auto stageError = [&](const TrustRegionEvaluation& point) -> double { return shapeStage ? point.breakdown.shapeLoss : point.fitness; }; @@ -2086,7 +1871,6 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() } // 有效改善后更新累计基准，并清除停滞计数。 - globalFallbackAttempted = false; effectiveImprovementBaseline = fitness; consecutiveIneffectiveSteps = 0; stagnationConfirmationRequested = false; @@ -2096,10 +1880,6 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() // 两个目标均沿用原 LM 的有效改善门槛及重建后停滞确认。 auto recordIneffectiveStep = [&]() -> bool { ++consecutiveIneffectiveSteps; - if(!globalFallbackAttempted) { - return false; - } - globalFallbackAttempted = false; if(consecutiveIneffectiveSteps < maximumIneffectiveSteps) { return false; } @@ -2308,7 +2088,8 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() return true; }; - for(int phase = 0; phase < 2 && !m_shouldStop && completedIterations < m_maxIterations; ++phase) { + for(int phase = skipShapeStage ? 1 : 0; + phase < 2 && !m_shouldStop && completedIterations < m_maxIterations; ++phase) { shapeStage = phase == 0; phaseIterations = 0; maximumEvaluations = m_totalEvaluations + phaseEvaluationBudget; @@ -2323,7 +2104,6 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() consecutivePoorPredictions = 0; modelRebuiltAtMinimumRadius = false; stagnationConfirmationRequested = false; - globalFallbackAttempted = false; jacobian.clear(); rebuildRequested = true; rebuildReason = shapeStage ? QT_TR_NOOP("full sensitivity at shape LM entry") @@ -2336,7 +2116,8 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() DEBUG_OUT(tr("LM phase budget: %1 remaining shared iterations, %2 evaluations.") .arg(m_maxIterations - completedIterations).arg(phaseEvaluationBudget)); writeTraceRow(completedIterations, -1, "stage_switch", current.parameters, current.fitness, - true, 0, shapeStage ? "height_to_shape_lm" : "shape_to_total", ¤t.breakdown); + true, 0, shapeStage ? "height_to_shape_lm" : (skipShapeStage ? "height_to_total" : "shape_to_total"), + ¤t.breakdown); while(!m_shouldStop && completedIterations < m_maxIterations && m_totalEvaluations < maximumEvaluations) { m_currentIteration = completedIterations; @@ -2374,18 +2155,8 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() ? current.breakdown.shapeResiduals : current.breakdown.residualVector; const int rowOffset = shapeStage ? current.breakdown.residualVector.size() : 0; const QVector > objectiveJacobian = jacobian.mid(rowOffset, objectiveResidual.size()); - QVector objectiveCoordinates; - if(shapeStage) { - // Fisher 窗口与形状残差使用同一组斜率区间中心。 - const int pointCount = current.breakdown.residualVector.size() / 2; - const int lag = autoFitShapeLag(pointCount); - for(int i = 0; i < pointCount - lag; ++i) - objectiveCoordinates.append((i + lag * 0.5) / (pointCount - 1)); - } - const QVector information = buildTrustRegionFisher( - objectiveJacobian, objectiveResidual, jacobianColumnValid, objectiveCoordinates); - // 两段都使用当前目标的全局信息，不按时间窗口另行选参。 - const TrustRegionFisher& global = information[kAutoFitTimeWindowCount]; + const TrustRegionNormalEquations global = buildTrustRegionNormalEquations( + objectiveJacobian, objectiveResidual, jacobianColumnValid); QVector selectedColumns; QVector coordinateStep; double predictedReduction = 0.0; @@ -2395,8 +2166,7 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() if(jacobianColumnValid[column] && global.matrix[column][column] > 0.0) selectedColumns.append(column); } - globalFallbackAttempted = true; - if(selectedColumns.isEmpty() || !buildTrustRegionFisherStep( + if(selectedColumns.isEmpty() || !buildTrustRegionStep( global, selectedColumns, current.coordinates, damping, trustRadius, minimumCoordinateStep, &coordinateStep, &predictedReduction)) { selectedColumns.clear(); @@ -2426,7 +2196,7 @@ StopReasonLM nmCalculationAutoFitLM::runTrustRegionFitting() for(int column = 0; column < dimensions; ++column) { candidateCoordinates[column] += coordinateStep[column]; } - // 窗口和参数索引仅写入已有跟踪文件，不向拟合日志窗口增加分段信息。 + // 参数索引保留在跟踪文件中，便于检查每次联合调整的参数。 QStringList selectedParameterIndices; for(int i = 0; i < selectedColumns.size(); ++i) { selectedParameterIndices << QString::number(m_enabledParamIndices[selectedColumns[i]]); @@ -3300,8 +3070,8 @@ double nmCalculationAutoFitLM::calculateLogLogCurveError( const QVector >& target, const QVector >& result) { - // 首次有效评价后固定公共时间范围。窗口与上下、左右、形状只负责诊断， - // 主目标仍由完整压力和导数残差计算，避免窗口重叠造成重复计权。 + // 首次有效评价后固定公共时间范围，保证各候选在相同时间点比较。 + // 总误差由完整压力和导数残差计算，形状阶段单独使用斜率残差。 // 整个计算过程均位于 log(time)-log(value) 坐标。 const double invalidLoss = 1.0e10; const double valueFloor = 1.0e-12; @@ -3427,7 +3197,7 @@ double nmCalculationAutoFitLM::calculateLogLogCurveError( } // 仅首次有效评价使用交集建立基准；失败试算不能冻结区间，后续候选 - // 必须覆盖完整基准，不允许靠丢失首尾点缩小误差或改变窗口位置。 + // 必须覆盖完整基准，不允许靠丢失首尾点缩小误差。 const bool comparisonRangeFixed = m_comparisonTimeMin > 0.0; double overlapMinX = comparisonRangeFixed ? m_comparisonTimeMin : qMax(targetMinX, resultMinX); @@ -3453,7 +3223,6 @@ double nmCalculationAutoFitLM::calculateLogLogCurveError( const int lag = autoFitShapeLag(count); const double span = qLn(overlapMaxX) - qLn(overlapMinX); QVector residuals[2]; - QVector targetLogs[2], resultLogs[2]; double biases[2] = {0.0, 0.0}; for(int component = 0; component < 2; ++component) { for(int i = 0; i < count; ++i) { @@ -3466,9 +3235,7 @@ double nmCalculationAutoFitLM::calculateLogLogCurveError( time, &resultValue)) return false; const double residual = resultValue - targetValue; residuals[component].append(residual); - targetLogs[component].append(targetValue); - resultLogs[component].append(resultValue); - // 对数时间梯形权重等价于互补窗口加权求和，避免密集段主导高度。 + // 使用对数时间梯形权重，避免密集段主导高度。 biases[component] += residual * ((i == 0 || i == count - 1) ? 0.5 : 1.0) / (count - 1); } @@ -3489,7 +3256,6 @@ double nmCalculationAutoFitLM::calculateLogLogCurveError( } } objective->shapeLoss = qSqrt(trustRegionSquaredNorm(objective->shapeResiduals)); - populateEarlyWellboreMetrics(objective, targetLogs, resultLogs, span); return isFiniteNumber(objective->shapeLoss); }; @@ -4119,8 +3885,6 @@ double nmCalculationAutoFitLM::calculateLogLogCurveError( isFiniteNumber(breakdown.total) && breakdown.total >= 0.0; if(breakdown.valid && breakdown.total < 1.0e9) { - breakdown.timeWindows = calculateAutoFitTimeWindows( - breakdown.residualVector, overlapMinX, overlapMaxX); if(!comparisonRangeFixed) { // 整个目标及诊断均有效后才提交基准，中点回退可重新建立区间。 m_comparisonTimeMin = overlapMinX;