LAUSR

Aiming at real-time monitoring of valve motion online in a new engine valve train that replaces the traditional cam with a self-developed new electromagnetic linear actuator, this paper presents a system scheme for motion monitoring of the electromagnetic linear actuators based on the Internet of Things and support vector machine (SVM) algorithm, which can effectively monitor the running state of the electromagnetic linear actuator and the valve. The system uses the lower computer to collect the current of electromagnetic linear actuator, and real-time transmits the data to the upper computer in the monitoring center. The upper computer firstly extracts the eigenvector of the motion state of the actuator by wavelet packet decomposition method, and then uses the artificial bee colony algorithm (ABC) to optimize the model kernel function parameters and penalty factor C of support vector machine, and establishes ABC-SVM electromagnetic linear actuator’s motion state model and training. In this paper, the method is compared with the direct-collected wire-controlled detection method. The results show that the system can accurately and quickly monitor and analyze the electromagnetic linear actuator and engine valve operating state, so it is feasible.