基于机器视觉的压纹机压力辊磨损度智能预测数据

压纹机压力辊磨损度指压力辊表面因长期机械摩擦导致的材料损耗程度，直接影响压纹质量和设备寿命。本监测数据有以下应用场景：在企业内部，本行业所有企业可通过实时监测磨损度指标，提升设备故障预判准确率，减少非计划停机时长。还可以结合磨损度预测数据优化生产排程，提升设备综合效率。在企业外部，模型适配造纸、金属轧制等依赖压力辊的制造业场景。还可将向设备制造商输出磨损度算法接口，驱动压力辊结构改良。1、数据收集：数据采集来源于工业相机、边缘检测算法和加速度传感器，每日实时采集压纹机磨损区域面积、压力辊初始表面积和裂纹长度等运行参数，对压纹机设备采集到的数据进行降噪、清洗、加工后进行处理。 2、数据处理：磨损面积异常程度=磨损区域面积/压力辊初始表面积，裂纹长度异常程度=最长裂纹长度/裂纹长度阈值，颜色差异异常程度=现表面颜色/初始表面颜色，振动频率异常程度=压力辊振动频率/振动基准频率，磨损度=磨损面积异常程度*磨损面积系数+裂纹长度异常程度*裂纹长度系数+颜色差异异常程度*颜色差异系数+振动频率异常程度*振动频率系数，四个系数需通过机器学习训练确定，总和为1。3、磨损度越小，表明设备越健康。磨损度大于等于 2.5，这代表了设备状态为故障，应立即停机检修；磨损度小于等于 1.8，这代表了设备状态为正常，应维持常规运维计划；磨损度在1.8至2.5范围内，这代表了设备状态为预警，应加强巡检频次。The wear degree of the embossing machine's pressure roller refers to the material loss on the roller surface caused by long-term mechanical friction, which directly affects the embossing quality and equipment service life. This monitoring data has the following application scenarios: 1. Internal enterprise scenarios: All enterprises in this industry can improve the accuracy of equipment fault prediction and reduce unplanned downtime by real-time monitoring of the wear degree index. It can also be combined with wear degree prediction data to optimize production scheduling and improve overall equipment efficiency. 2. External enterprise scenarios: The model can be adapted to manufacturing scenarios that rely on pressure rollers, such as papermaking and metal rolling. It can also output wear degree algorithm interfaces to equipment manufacturers to drive the structural improvement of pressure rollers. 1. Data Collection: Data is collected from industrial cameras, edge detection algorithms and acceleration sensors. Operating parameters including the wear area of the embossing machine, the initial surface area of the pressure roller and crack length are collected in real time on a daily basis. The data collected by the embossing machine equipment is processed after noise reduction, cleaning and preprocessing. 2. Data Processing: Abnormal wear area extent = wear area of the pressure roller / initial surface area of the pressure roller; Abnormal crack length extent = maximum crack length / crack length threshold; Abnormal color difference extent = current surface color / initial surface color; Abnormal vibration frequency extent = vibration frequency of the pressure roller / vibration reference frequency. The wear degree is calculated as: Wear Degree = (Abnormal wear area extent * Wear Area Coefficient) + (Abnormal crack length extent * Crack Length Coefficient) + (Abnormal color difference extent * Color Difference Coefficient) + (Abnormal vibration frequency extent * Vibration Frequency Coefficient). The four coefficients must be determined through machine learning training, with their total sum equal to 1. 3. The smaller the wear degree, the healthier the equipment condition. When the wear degree is greater than or equal to 2.5, the equipment is in a faulty state and should be shut down for maintenance immediately; when the wear degree is less than or equal to 1.8, the equipment is in a normal state and conventional operation and maintenance plans should be maintained; when the wear degree is within the range of 1.8 to 2.5, the equipment is in a pre-warning state and the frequency of inspections should be increased.

搜集汇总

背景与挑战

背景概述

该数据集基于机器视觉和传感器技术，采集压纹机压力辊的磨损相关数据，包括磨损面积、裂纹长度、颜色差异和振动频率等22个字段，共22644条记录，每日更新。通过机器学习算法计算磨损度，用于预测设备状态（正常、预警、故障），支持制造业设备维护和优化生产排程。