传感器are well recognized as key components of any industrial digital strategy. In fact, for years now, the deployment of more and more sensors to capture increasingly large amounts of data for analysis has been a principal recommendation for manufacturers across all industry verticals.
This has been especially true for asset condition monitoring (CM) and predictive maintenance (PM) applications. As a result, many mid-sized manufacturers are not very far along their digital transformation journey because they often cannot afford to install increasingly larger amounts of costly industrial sensors.
To get around the sensor cost issue, Lenze has been focusing on teaching customers how to get this added data for CM and PM applications from devices they already have installed.
At the SPS (Smart Production Solutions) 2019 event in Nuremberg, Germany,Prof-Dr. Holger Borcherding, head of innovation atLenze指出，该公司正在帮助OEM和其他最终用户通过使用Lenze的预先测试的算法来提取现有数据来源的附加信息价值，帮助机械工程师将其工艺专业知识和计算机知识转化为条件监测模型这将提高效率。“
利用Lenze Booth中的2轴机器人的示例，Lenze显示了基于模型和基于数据的方法来使用来自机器人驱动器的数据的条件监控。
In the model-based example, actual values from the robot’s controller are measured are compared with those from Lenze’s mathematical description of the robot. If certain tolerances are exceeded, this is interpreted as a fault. In the data-based approach, a Lenze-developed algorithm learns the robot’s behavior based on the influences of parameters, such as velocity, acceleration, torque, position, and current consumption. The real values are then compared with the description to define deviations.
Prof-Dr. Holger Borcherding, head of innovation at Lenze.在Lenze在这两种方法的演示期间，暴露了在皮带驱动器上的主轴和磨损上的摩擦增加的问题。“这些异常可以通过电流和扭矩值在两种情况下检测到，这是通过频率分析中的值或通过异常的绝对增加来检测到这一点，”说Borcherding. “The condition monitoring application then raises the alarm in both cases and shows the causes on a dashboard.”
Borcherdingexplained that the model-based evaluation usually takes place on the control system, because it does not require any significant computing power. However, the use of Lenze’s machine learning and artificial intelligence technologies in the data-based analyses typically require its calculations to be conducted in Lenze’s x4 cloud application with data sent via Lenze’s x500 gateway.Borcherding确实注意到了这一点data-based evaluations can also be performed locally using Lenze’s c750 cabinet controller.
Underscoring his point thatefficient condition monitoring is possible based on the interpretation of existing data,Borcherdingstressed that“no additional sensor technology is needed. Instead, the machine’s drives can work as sensors. With our automation portfolio of hardware, software, networks, cloud applications, and consulting expertise, Lenze can help manufacturers become data scientists for their machines."
