Nonastreda: Multimodal Dataset for Identifying Tool Wear Condition
收藏资源简介：
# Nonastreda: 9 Multimodal Dataset Featuring Time Series and Image Data for Flank Tool Wear Classification and Regression * Detailed description: 'Data in Brief' Journal (available soon) * Repository: https://github.com/hubtru/Impala * Repository: https://github.com/hubtru/Girape * Notebooks for converting forces_xyz_raw.mat into spectrograms, scalograms or wavelets: https://github.com/hubtru/Girape/tree/main/scripts # Overview: Nonastreda (Nona) * 'Nona' from Latin "ninth" * Dataset Size: 512 samples (instances, observations) * Modalities: 9 modalities * Tasks: * Classification: 3 classes (sharp, used, dulled) * Regression: 3 targets (flank wear [µm], gaps [µm], overhang [µm]) * Additional subtasks: * Uni/Multi-Modal Classification * Multilabel Regression * Anomaly Detection * Remaining Useful Life (RUL) Estimation * Signal Drift Measurement * Zero-Shot Flank Tool Wear Classification * Diagnostic Feature Engineering * Domain: industrial flank tool wear of the milling machine * Input (per sample): * Images: 1 tool image, 1 chip image, 1 workpiece image * Mel-Spectrograms: x, y, z axes (3 images) * Complex Morlet Scalograms: x, y, z axes (3 images) * Extra Modalities: raw (time-series) force signals in x, y, z axes * Output: * Machine state classes: sharp, used, dulled * Regression targets: flank wear [µm], gaps [µm], overhang [µm] * Evaluation metrics: * Classification: accuracies, precision, recall, F1-Score, ROC curve * Regression: MAE, MSE, RMSE * Data splitting: * Protocol: 10-Fold Cross Validation * Training and Validation: data from 9 tools * Testing: data from the 10th tool * Results: accuracy averaged over ten splits * The dataset includes measurements from ten tools Extra Time-Series Modality * Raw forces signal in x, y, z axes is provided in `forces_xyz_raw.mat` file. * The `*.mat` file can be used with scripts from the Girape repository to generate spectrograms, scalograms, and wavelets. * Source force signals (Fx, Fy, Fz) allow experimentation with new types of feature engineering and embeddings, such as Shannon, Daubechies, or Morlet wavelets. * Sampling rate for force signals: 1 kHz. * forces_xyz.mat + Girape/scripts -> spectrograms or scalograms or wavelets Future Work * Improvements of (zero-shot flank) tool wear classification and regression. * Incorporating raw force signals (Fx, Fy, Fz) into multimodal studies. * Calculating new modalities using the raw force signals (Fx, Fy, Fz). * Conducting experiments on: * Anomaly Detection * Remaining Useful Life (RUL) estimation * Signal Drift measurement * Designing Diagnostic Feature Engineering. * Modalities Correlation Analysis. # Data Structure Nonastreda/ │ ├── chip/ ├── scal/ │ ├── x/ │ ├── y/ │ └── z/ ├── spec/ │ ├── x/ │ ├── y/ │ └── z/ ├── tool/ │ ├── work/ │ ├── labels.csv ├── labels_reg.csv └── forces_xyz_raw.mat
# Nonastreda：面向刀具后刀面磨损分类与回归任务的9模态时序与图像多模态数据集 * 详细说明：已投稿至《Data in Brief》期刊（待刊出） * 数据集仓库：https://github.com/hubtru/Impala * 数据集仓库：https://github.com/hubtru/Girape * 用于将`forces_xyz_raw.mat`转换为频谱图、尺度图或小波图的Notebook脚本：https://github.com/hubtru/Girape/tree/main/scripts # 数据集概览：Nonastreda（简称Nona） * 名称中的“Nona”源自拉丁语“第九” * 数据集规模：共512条样本（实例/观测值） * 模态类型：共9种模态 * 支持任务： * 分类任务：包含3个类别（锋利、正常使用、磨损钝化） * 回归任务：包含3个预测目标（后刀面磨损量[µm]、间隙量[µm]、悬伸量[µm]） * 附加子任务： * 单模态/多模态分类 * 多标签回归 * 异常检测 * 剩余使用寿命（RUL）估计 * 信号漂移度量 * 零样本刀具后刀面磨损分类 * 诊断特征工程 * 应用领域：铣床刀具后刀面工业磨损场景 * 单样本输入数据： * 图像类：刀具图像、切屑图像、工件图像各1张 * 梅尔频谱图（Mel-Spectrogram）：X、Y、Z三轴对应3张图像 * 复Morlet尺度图（Complex Morlet Scalogram）：X、Y、Z三轴对应3张图像 * 额外模态：X、Y、Z三轴原始时序力信号 * 输出标签： * 机床状态类别：锋利、正常使用、磨损钝化 * 回归目标值：后刀面磨损量[µm]、间隙量[µm]、悬伸量[µm] * 评估指标： * 分类任务：准确率、精确率、召回率、F1分数、受试者工作特征（ROC）曲线 * 回归任务：平均绝对误差（MAE）、均方误差（MSE）、均方根误差（RMSE） * 数据划分协议： * 划分方案：十折交叉验证 * 训练与验证集：取自9把刀具的数据 * 测试集：取自第10把刀具的数据 * 结果计算方式：对10次拆分的准确率取平均值 * 本数据集共包含10把刀具的实测数据 # 额外时序模态说明 * X、Y、Z三轴原始力信号存储于`forces_xyz_raw.mat`文件中。 * 可结合Girape仓库中的脚本，将该MAT文件转换为频谱图、尺度图及小波图。 * 原始力信号（Fx、Fy、Fz）支持开展新型特征工程与嵌入实验，例如基于香农小波、Daubechies小波或Morlet小波的相关研究。 * 力信号采样率为1 kHz。 * 可通过`forces_xyz.mat`结合Girape/scripts脚本生成频谱图、尺度图或小波图。 # 未来研究方向 * 优化（零样本）刀具后刀面磨损分类与回归模型性能 * 将原始力信号（Fx、Fy、Fz）融入多模态研究 * 基于原始力信号（Fx、Fy、Fz）构建新型模态 * 开展以下实验研究： * 异常检测 * 剩余使用寿命（RUL）估计 * 信号漂移度量 * 设计诊断特征工程方案 * 开展模态相关性分析 # 数据组织结构 Nonastreda/ │ ├── chip/ ├── scal/ │ ├── x/ │ ├── y/ │ └── z/ ├── spec/ │ ├── x/ │ ├── y/ │ └── z/ ├── tool/ │ ├── work/ │ ├── labels.csv ├── labels_reg.csv └── forces_xyz_raw.mat
