Nonastreda: Multimodal Dataset for Identifying Tool Wear Condition
收藏DataCite Commons2025-04-01 更新2025-04-16 收录
下载链接:
https://data.mendeley.com/datasets/m892d2wtzh
下载链接
链接失效反馈官方服务:
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:面向侧面刀具磨损分类与回归的9模态多模态数据集,融合时序与图像数据
* 详细说明:《Data in Brief》期刊(即将上线)
* 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)
* 名称由来: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
* 任务类型:
* 分类任务:涵盖3个类别(锋利(sharp)、使用中(used)、钝化(dulled))
* 回归任务:包含3个回归目标(侧面刀具磨损量(flank wear)[µm]、间隙量(gaps)[µm]、悬臂量(overhang)[µm])
* 额外子任务:
* 单模态/多模态分类
* 多标签回归
* 异常检测(Anomaly Detection)
* 剩余使用寿命(Remaining Useful Life, RUL)预估
* 信号漂移度量
* 零样本侧面刀具磨损分类(Zero-Shot Flank Tool Wear Classification)
* 诊断特征工程(Diagnostic Feature Engineering)
* 应用领域:铣床工业侧面刀具磨损场景
* 单样本输入:
* 图像类:刀具图像、切屑图像、工件图像各1张
* 梅尔频谱图(Mel-Spectrograms):x、y、z三个轴方向各1张,共3张
* 复Morlet尺度图(Complex Morlet Scalograms):x、y、z三个轴方向各1张,共3张
* 额外模态:x、y、z三个轴方向的原始(时序)力信号
* 输出内容:
* 机器状态类别:锋利、使用中、钝化
* 回归目标:侧面刀具磨损量[µm]、间隙量[µm]、悬臂量[µm]
* 评估指标:
* 分类任务:准确率(Accuracy)、精确率(Precision)、召回率(Recall)、F1分数(F1-Score)、受试者工作特征曲线(ROC Curve)
* 回归任务:平均绝对误差(Mean Absolute Error, MAE)、均方误差(Mean Squared Error, MSE)、均方根误差(Root Mean Squared Error, RMSE)
* 数据划分方案:
* 划分协议:10折交叉验证
* 训练集与验证集:取自9把刀具的数据
* 测试集:取自第10把刀具的数据
* 结果评估:对10次划分的结果取平均准确率
* 本数据集共包含10把刀具的测量数据
## 额外时序模态
* x、y、z轴的原始力信号存储于`forces_xyz_raw.mat`文件中
* 可结合Girape仓库中的脚本,对该`.mat`文件进行处理,生成频谱图、尺度图与小波图
* 原始力信号(Fx、Fy、Fz)可用于开展新型特征工程与嵌入方法的实验,例如香农(Shannon)小波、Daubechies小波或Morlet小波
* 力信号采样率:1 kHz
* 通过`forces_xyz_raw.mat`与Girape/scripts脚本,可生成频谱图、尺度图或小波图
## 未来研究方向
* 优化(零样本)侧面刀具磨损分类与回归任务性能
* 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:
* 异常检测
* 剩余使用寿命(RUL)预估
* 信号漂移度量
* 开展诊断特征工程相关研究
* 开展模态相关性分析
# 数据集目录结构
Nonastreda/
│
├── chip/ # 切屑图像文件夹
├── scal/ # 复Morlet尺度图文件夹
│ ├── x/ # x轴尺度图子文件夹
│ ├── y/ # y轴尺度图子文件夹
│ └── z/ # z轴尺度图子文件夹
├── spec/ # 梅尔频谱图文件夹
│ ├── x/ # x轴频谱图子文件夹
│ ├── y/ # y轴频谱图子文件夹
│ └── z/ # z轴频谱图子文件夹
├── tool/ # 刀具图像文件夹
│
├── work/ # 工件图像文件夹
│
├── labels.csv # 分类标签文件
├── labels_reg.csv # 回归标签文件
└── forces_xyz_raw.mat # 原始力信号文件
提供机构:
Mendeley Data
创建时间:
2025-01-09
搜集汇总
背景与挑战
背景概述
Nonastreda是一个多模态数据集,包含512个样本和9种模态数据,用于工业铣床刀具磨损状态的分类和回归任务。数据集支持多种任务,包括分类(锐利、使用、钝化)、回归(磨损、间隙、悬垂)以及异常检测等,并提供了详细的数据结构和评估指标。
以上内容由遇见数据集搜集并总结生成



