遇见数据集

Tool Wear Emitted Sound Data

收藏
Mendeley Data2024-05-10 更新2024-06-29 收录
官方服务:

资源简介:

A PCB 130D20 microphone is kept in a stand and facing towards the tool tip to capture the emitted sound. The microphone is connected to the computer through a specially designed signal conditioner. GoldWave software is used to record the captured sound with sampling frequency set to 44100Hz. A series of machining experiments were conducted on a Turning machine(XLTURN from MTAB) with Carbide Insert and aluminium work piece of 38mm diameter. Throughout the experiment a constant feed rate set at 0.5 mm/rotation was uniformly maintained. First, the freerunning sound for the spindle rotational speed of 400 rev/min was recorded, without the machining operation. Keeping the spindle rotational speed at 570 rev/min, the sound emitted due to machining with a fresh tool was recorded separately for the depth of cut of 1 mm. This recording process was repeated separately for slightly worn tool with 0.2mm flank wear and severely worn tool with 0.4mm flank wear]. The 12-second-long sound signal is split into 12 one second sound signals for the subsequent signal processing using HHT. Each one second signal contains 44100 sampling data.

将PCB 130D20型麦克风固定于支架上,正对刀具刀尖以采集切削辐射噪声。该麦克风通过定制信号调理器连接至计算机,采用GoldWave软件录制采集到的声音信号,采样率设置为44100赫兹。实验在MTAB公司生产的XLTURN型车床上开展,采用硬质合金刀片与直径38mm的铝合金工件作为加工对象。实验全程维持恒定进给率0.5毫米/转。首先记录主轴转速为400转/分时的空转噪声,此时未进行任何切削加工。随后将主轴转速固定为570转/分,先针对新刀具在背吃刀量1mm的工况下录制切削噪声,再分别对后刀面磨损量0.2mm的轻微磨损刀具、后刀面磨损量0.4mm的严重磨损刀具重复上述录制流程。将每条时长12秒的声音信号拆分为12段1秒长的子信号,用于后续采用希尔伯特-黄变换(Hilbert-Huang Transform,HHT)的信号处理流程;每段1秒的子信号包含44100个采样数据点。

创建时间:
2024-05-08
搜集汇总
数据集介绍
Tool Wear Emitted Sound Data 数据集图片
背景与挑战
背景概述
该数据集是一个用于刀具磨损监测的声音数据集,通过高精度麦克风在车床上采集不同磨损状态(新刀具、轻微磨损和严重磨损)下的声音信号,采样频率为44100Hz。数据以WAV格式提供,每个信号被分割为1秒片段,适用于基于希尔伯特-黄变换等非线性信号处理和机器学习方法进行刀具磨损分析。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务