科勘科技设备预测性维护系统PMA方案基于SCHNEIDER_智慧城市_产品

科勘科技设备预测性维护系统PMA方案基于SCHNEIDER

服务费用：物流费物流费物流费调试安装费
发货时间：24小时（有货状态）

点击定制确认订单支付费用 24小时发货

我们涉及的工业设备如减速机和齿轮箱、空压机、泵、风机、电机、离心机及皮带输送机等，我们采用高频振动传感器（MES4V3A、MES4V3C）与MEG9XXX边缘计算网关配合，基于DCS/PLC工艺特征数据的采集。将这些数据上传至IOT CLOUD，然后进入专家库，体现出预测性维护顾问PMA，APP端展示数据，WEB端将这些挖掘数据提供给制造方和终端用户。制造商服务中心进行售后服务，终端用户运维中心可以运维与制造方互动。

利用DBSCAN等聚类工具，筛选出有价值的工况后，对分工况的特征进行灵活的阈值设定利用PCA主成分分析方法去识别主要特征频率，从而诊断设备故障。

某啤酒糖化工艺设备PMA投资收益评估ROI，降低了维护的人工成本（5%）降低备品备件的采购频率，减少浪费开支（10%）降低了与OEM厂商之间的沟通与协调成本（3%）客户内部团队的精简或工作重心的转移（2%）减少传统外协维保服务成本（10%）

有色金属行业某龙头企业，针对其关键设备如风机、闪速炉、搅拌磨机、循环泵、制氮机、制氧机、干燥机等设备进行故障预测和健康运维管理，推动工厂的数字化转型。

水泥项目生产大型电机故障预测及诊断，当天从系统明显的看到，峭度特征值在变小，但是一天后峭度特征值又明显增加且有逐步变大的趋势，说明主要问题还没有解决，故障依然存在。平台再次自动建议客户对电机进行松动和对中处理并对设备进行维修。

1.设备正常工作状态（10月1日-11月6日）：峭度特征值处于一个平稳的状态；

2.设备故障发展期（11月6日-11月13日）：径向垂直端（三轴传感器的优势）的峭度处于一个上升的趋势

3.设备故障期（11月13日至11月22日）：峭度值变大，且超过故障诊断模型的阈值；

客户对电机进行对中维修后，峭度特征值明显下降，并一直平稳工作。预测性维护系统成功帮助客户避免一次大的运行事故的发生，客户对于系统的这次故障诊断非常认可。

设备健康管理依托AM资产管理平台使用IoT与AI能力，提高运维能力，减少停机时间，降低风险和成本，延长资产生命周。期并优化资产性能，实现全程可视化管理，构建资产管理生态体系。

For the industrial equipment we are involved in, such as reducer and gearbox, air compressor, pump, fan, motor, centrifuge and belt conveyor, we use high-frequency vibration sensors (MES4V3A, MES4V3C) to cooperate with MEG9XXX edge computing gateway, based on the acquisition of DCS/PLC process feature data. Upload these data to IOT CLOUD, and then enter the expert database to reflect the predictive maintenance consultant PMA. The APP displays the data, and the WEB provides these mining data to manufacturers and end users. The manufacturer service center provides after-sales service, and the end user operation and maintenance center can interact with the manufacturer.

Using clustering tools such as DBSCAN, valuable operating conditions are selected, and flexible threshold settings are applied to the characteristics of different operating conditions. PCA principal component analysis is used to identify the main feature frequencies and diagnose equipment faults.

ROI of PMA investment return evaluation for a certain beer saccharification process equipment, reduced maintenance labor costs (5%), reduced procurement frequency of spare parts, reduced waste expenses (10%), reduced communication and coordination costs with OEM manufacturers (3%), streamlined internal customer teams or shift of work focus (2%), and reduced traditional outsourcing maintenance service costs (10%)

A leading enterprise in the non-ferrous metal industry is conducting fault prediction and healthy operation management for its key equipment such as fans, flash furnaces, stirring mills, circulation pumps, nitrogen generators, oxygen generators, dryers, etc., promoting the digital transformation of the factory.

Prediction and diagnosis of large-scale motor faults in cement project production. On the same day, it was clearly seen from the system that the kurtosis characteristic value was decreasing, but after one day, the kurtosis characteristic value increased significantly and gradually increased, indicating that the main problem has not been solved and the fault still exists. The platform once again automatically recommends customers to loosen and center the motor and repair the equipment.

1. The equipment is in normal working condition （October 1st to November 6th）: the kurtosis characteristic value is in a stable state;

2. Equipment malfunction development period （November 6-13）: The kurtosis of the radial vertical end (advantage of three-axis sensors) is on an upward trend

3. Equipment failure period （November 13th to November 22nd）: The kurtosis value increases and exceeds the threshold of the fault diagnosis model;

After the customer carried out center maintenance on the motor, the kurtosis characteristic value significantly decreased and remained stable. The predictive maintenance system has successfully helped customers avoid a major operational accident, and the customer highly appreciates the system's fault diagnosis.

Equipment health management relies on the AM asset management platform to utilize IoT and AI capabilities, improve operational capabilities, reduce downtime, reduce risks and costs, and extend asset lifecycle. Optimize asset performance, achieve full process visual management, and build an asset management ecosystem.

IMG_7d4b8d846a444629ac2181b04a299d3d