A power-based online detection method for abnormal motion of industrial manipulators

Abstract

The invention discloses an online detection method for abnormal motion of an industrial mechanical arm based on power. The method is realized based on an online detection system for abnormal motion of an industrial mechanical arm. The system includes a position data acquisition module, a power data acquisition module and an abnormal detection module; two The data acquisition module obtains the position and power sampling data of the manipulator during normal operation as the model initialization sample; the anomaly detection module uses the sample data to fit the generalized dynamic model of the industrial manipulator to realize the specialization of the power consumption model, and further bases on the Whether the accumulated deviation or instantaneous deviation between the predicted power obtained by the consumption model and the actual consumed power exceeds the specified threshold to realize anomaly detection and model update. The method of the invention can carry out online detection of false data injection, replay, man-in-the-middle and other concealed attacks aimed at realizing by tampering data without interfering with the normal operation of the mechanical arm.

Description

technical field [0001] The invention relates to the field of industrial control system security, in particular to an online detection method for abnormal motion of an industrial mechanical arm based on power. Background technique [0002] With the deep integration of industrialization and informatization, more and more industrial robotic arms are connected to the industrial Internet of Things platform, and its control system is therefore facing more information security risks, which may cause casualties, equipment damage, and reduce production. Physical security issues such as efficiency. How to detect anomalies in the face of attackers' malicious attacks has become an important problem in the current anomaly detection research. [0003] At present, the anomaly detection method for industrial manipulators is mainly considered from the following two perspectives: 1) Based on the operating status information of industrial manipulators: by collecting the operating state inform...

AI Technical Summary

Problems solved by technology

[0004] There are many problems in the existing anomaly detection technology when it is attacked (such as replay attack, data injection attack), including: 1) The state information uploaded by the method based on the operation state information of the industrial manipulator may be tampered with when facing the attack ( replay, injection, etc.), resulting in unreliable data, 2) gyroscope-based methods need to spend a lot of money on the installation of related sensors, for example, gyroscope-based abnormal detection needs to shut down the industrial robot arm, and install the gyroscope To the end effector of the robotic arm, so the cost is high. 3) The camera-based method has the problem of excessive video frame data dimensions, resulting in a decrease in real-time detection. 4) The method based on the microphone (collecting audio) is vulnerable to factory noise The problem of interference leads to a decrease in the accuracy of anomaly detection

Images