Research And Application On Sensor Technology & Signal Processing For Fault Diagnosis In Mechanical Equipments

NC machining is the typical application of NC technology in industrial production, "intelligention" is its development way. Its content mostly is NC machining processing monitoring and fault diagnosis.This paper constructs a multi-sensor-based process monitoring system for NC machining, introduces means of signal acquisition of machine tool and hardware of acquisition installation, discusses means of signal pretreatment and parameters disposal. The current, voltage, vibration and acoustic signals of NC machining are acquired and analyzed. Extracting features and finding the change current of signal, to provide Real-time reliable basic data for optimizing technical parameter, increasing efficiency of production, forecasting technical quality and avoiding faults.The main body of system is computer which real-time collects features parameter of processing, and analyzing. Artificial Neural Network (ANN) is applied to propose the parameters using in machining. In order to satisfy requirements for individual operations, fuzzy ARTMAP neural network is used to implement the continuous learning based on samples of cutting conditions that obtained from previously learning and recommended from a machining data handbook. Those samples could be substituted by better cutting conditions by a proposed replacement algorithm. The software system contents data acquisition signal processing and process monitoring, which is the main part of the system.We experimented at HL-32,and we can draw a conclusion that the system can real-time collects features signal and identifies processing state, which indicates that research and application on sensor technology & signal processing for fault diagnosis in mechanical equipments is important and the system is effective and feasible...